Graphify-Labs/graphifyPublic

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

AI summary: Data transformation engine for converting unstructured text into structured, queryable knowledge graphs automatically.

Stars
151.2K
+49 today
Forks
14.5K
Watchers
439
Open issues
754
Open PRs
901
Contributors
~414
Commits
3K
Branches
15
Views (30d)
32

PythonApache-2.0Created Apr 3, 2026Last push todayLatest release v0.9.108+3.5K stars this week+18.3K this month

Quick answers

What is graphify?
Data transformation engine for converting unstructured text into structured, queryable knowledge graphs automatically.
What does graphify do?
Graphify extracts entities, relationships, and complex semantic meaning from large volumes of unstructured document text. It utilizes language models to identify obscure connections that rigid regex parsers typically miss. The engine structures this extracted data into standardized node and edge formats suitable for direct ingestion by graph databases. It handles the entity resolution process to merge duplicate references into single, highly connected conceptual nodes. By automating the extraction pipeline, it allows organizations to map complex internal knowledge networks efficiently.
Who is graphify for?
Data engineers, knowledge managers, and AI researchers building advanced information retrieval systems. Familiarity with graph database concepts is necessary.
How do I get started with graphify?
https://github.com/Graphify-Labs/graphify
How popular is graphify on GitHub?
Graphify-Labs/graphify has 151,207 stars and 14,536 forks on GitHub, and gained 3,458 stars in the last 7 days.
What license does graphify use?
Graphify-Labs/graphify is released under the Apache-2.0 license.

Star history

since Jul 28, 2026
050K100K150KJul 2026Sep 2026Oct 2026Nov 2026
151.2K stars as of Nov 21, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

6 recorded
  • Nov 14, 2026New release v0.9.108 (previously v0.9.102).
  • Nov 5, 2026New release v0.9.102 (previously v0.9.96).
  • Oct 27, 2026New release v0.9.96 (previously v0.9.92).
  • Oct 17, 2026New release v0.9.92 (previously v0.9.80).
  • Oct 8, 2026New release v0.9.80 (previously v0.9.72).
  • Oct 4, 2026Previously tracked as safishamsi/graphify; its 1 daily snapshot and 42 trending appearances were merged into this profile. Stars: 98,319 on 2026-07-29 under the old name, 123,705 on 2026-10-04 (+25,386).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-16: 0 commits2025-11-17: 0 commits2025-11-18: 0 commits2025-11-19: 0 commits2025-11-20: 0 commits2025-11-21: 0 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 0 commits2026-03-13: 0 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 0 commits2026-03-17: 0 commits2026-03-18: 0 commits2026-03-19: 0 commits2026-03-20: 0 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 0 commits2026-03-31: 0 commits2026-04-01: 0 commits2026-04-02: 0 commits2026-04-03: 2 commits2026-04-04: 8 commits2026-04-05: 18 commits2026-04-06: 24 commits2026-04-07: 16 commits2026-04-08: 13 commits2026-04-09: 26 commits2026-04-10: 19 commits2026-04-11: 4 commits2026-04-12: 7 commits2026-04-13: 6 commits2026-04-14: 2 commits2026-04-15: 4 commits2026-04-16: 4 commits2026-04-17: 8 commits2026-04-18: 8 commits2026-04-19: 0 commits2026-04-20: 1 commit2026-04-21: 18 commits2026-04-22: 11 commits2026-04-23: 5 commits2026-04-24: 1 commit2026-04-25: 1 commit2026-04-26: 1 commit2026-04-27: 7 commits2026-04-28: 4 commits2026-04-29: 13 commits2026-04-30: 8 commits2026-05-01: 12 commits2026-05-02: 29 commits2026-05-03: 10 commits2026-05-04: 30 commits2026-05-05: 13 commits2026-05-06: 7 commits2026-05-07: 23 commits2026-05-08: 4 commits2026-05-09: 13 commits2026-05-10: 1 commit2026-05-11: 3 commits2026-05-12: 7 commits2026-05-13: 8 commits2026-05-14: 12 commits2026-05-15: 22 commits2026-05-16: 16 commits2026-05-17: 9 commits2026-05-18: 15 commits2026-05-19: 0 commits2026-05-20: 4 commits2026-05-21: 1 commit2026-05-22: 12 commits2026-05-23: 4 commits2026-05-24: 7 commits2026-05-25: 1 commit2026-05-26: 15 commits2026-05-27: 8 commits2026-05-28: 13 commits2026-05-29: 9 commits2026-05-30: 6 commits2026-05-31: 12 commits2026-06-01: 7 commits2026-06-02: 14 commits2026-06-03: 15 commits2026-06-04: 0 commits2026-06-05: 15 commits2026-06-06: 4 commits2026-06-07: 14 commits2026-06-08: 7 commits2026-06-09: 5 commits2026-06-10: 8 commits2026-06-11: 19 commits2026-06-12: 8 commits2026-06-13: 6 commits2026-06-14: 0 commits2026-06-15: 1 commit2026-06-16: 6 commits2026-06-17: 15 commits2026-06-18: 8 commits2026-06-19: 10 commits2026-06-20: 1 commit2026-06-21: 2 commits2026-06-22: 9 commits2026-06-23: 7 commits2026-06-24: 15 commits2026-06-25: 9 commits2026-06-26: 6 commits2026-06-27: 15 commits2026-06-28: 28 commits2026-06-29: 18 commits2026-06-30: 20 commits2026-07-01: 25 commits2026-07-02: 21 commits2026-07-03: 6 commits2026-07-04: 10 commits2026-07-05: 12 commits2026-07-06: 25 commits2026-07-07: 11 commits2026-07-08: 13 commits2026-07-09: 16 commits2026-07-10: 10 commits2026-07-11: 7 commits2026-07-12: 8 commits2026-07-13: 15 commits2026-07-14: 17 commits2026-07-15: 20 commits2026-07-16: 14 commits2026-07-17: 17 commits2026-07-18: 15 commits2026-07-19: 7 commits2026-07-20: 16 commits2026-07-21: 17 commits2026-07-22: 20 commits2026-07-23: 5 commits2026-07-24: 6 commits2026-07-25: 19 commits2026-07-26: 12 commits2026-07-27: 13 commits2026-07-28: 11 commits2026-07-29: 15 commits2026-07-30: 9 commits2026-07-31: 5 commits2026-08-01: 7 commits2026-08-02: 0 commits2026-08-03: 0 commits2026-08-04: 0 commits2026-08-05: 5 commits2026-08-06: 3 commits2026-08-07: 5 commits2026-08-08: 2 commits2026-08-09: 4 commits2026-08-10: 5 commits2026-08-11: 21 commits2026-08-12: 15 commits2026-08-13: 16 commits2026-08-14: 13 commits2026-08-15: 18 commits2026-08-16: 9 commits2026-08-17: 22 commits2026-08-18: 17 commits2026-08-19: 9 commits2026-08-20: 14 commits2026-08-21: 16 commits2026-08-22: 0 commits2026-08-23: 0 commits2026-08-24: 15 commits2026-08-25: 17 commits2026-08-26: 4 commits2026-08-27: 10 commits2026-08-28: 8 commits2026-08-29: 22 commits2026-08-30: 24 commits2026-08-31: 3 commits2026-09-01: 1 commit2026-09-02: 7 commits2026-09-03: 7 commits2026-09-04: 5 commits2026-09-05: 11 commits2026-09-06: 4 commits2026-09-07: 20 commits2026-09-08: 8 commits2026-09-09: 6 commits2026-09-10: 22 commits2026-09-11: 15 commits2026-09-12: 20 commits2026-09-13: 11 commits2026-09-14: 34 commits2026-09-15: 10 commits2026-09-16: 35 commits2026-09-17: 10 commits2026-09-18: 2 commits2026-09-19: 5 commits2026-09-20: 14 commits2026-09-21: 11 commits2026-09-22: 24 commits2026-09-23: 18 commits2026-09-24: 12 commits2026-09-25: 27 commits2026-09-26: 20 commits2026-09-27: 19 commits2026-09-28: 12 commits2026-09-29: 16 commits2026-09-30: 13 commits2026-10-01: 14 commits2026-10-02: 22 commits2026-10-03: 22 commits2026-10-04: 24 commits2026-10-05: 29 commits2026-10-06: 25 commits2026-10-07: 20 commits2026-10-08: 17 commits2026-10-09: 13 commits2026-10-10: 48 commits2026-10-11: 31 commits2026-10-12: 37 commits2026-10-13: 32 commits2026-10-14: 14 commits2026-10-15: 17 commits2026-10-16: 8 commits2026-10-17: 13 commits2026-10-18: 3 commits2026-10-19: 9 commits2026-10-20: 15 commits2026-10-21: 22 commits2026-10-22: 21 commits2026-10-23: 54 commits2026-10-24: 15 commits2026-10-25: 27 commits2026-10-26: 24 commits2026-10-27: 33 commits2026-10-28: 15 commits2026-10-29: 15 commits2026-10-30: 37 commits2026-10-31: 19 commits2026-11-01: 22 commits2026-11-02: 33 commits2026-11-03: 30 commits2026-11-04: 24 commits2026-11-05: 18 commits2026-11-06: 21 commits2026-11-07: 17 commits2026-11-08: 10 commits2026-11-09: 33 commits2026-11-10: 23 commits2026-11-11: 22 commits2026-11-12: 13 commits2026-11-13: 1 commit2026-11-14: 0 commits
2,959 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Landmark project

    151,207 stars

  • Very active

    2,959 commits in 52 weeks

  • Community-driven

    ~414 contributors

  • Well documented

    High community health score

  • Permissive license

    Apache-2.0

  • Continuous integration

    Automated checks passing

  • Repeat trending

    65 trending appearances

  • Top 10% tracked

    Rank 41 of 1243

What graphify does

Graphify extracts entities, relationships, and complex semantic meaning from large volumes of unstructured document text. It utilizes language models to identify obscure connections that rigid regex parsers typically miss. The engine structures this extracted data into standardized node and edge formats suitable for direct ingestion by graph databases. It handles the entity resolution process to merge duplicate references into single, highly connected conceptual nodes. By automating the extraction pipeline, it allows organizations to map complex internal knowledge networks efficiently.

Data engineers, knowledge managers, and AI researchers building advanced information retrieval systems. Familiarity with graph database concepts is necessary.

  • Semantic extraction: Utilizes language models to identify complex relationships within highly unstructured text.
  • Entity resolution: Merges duplicate references automatically to maintain clean, accurate knowledge graph nodes.
  • Format standardization: Outputs extracted relationships in clean formats optimized for immediate database ingestion.
  • Pipeline automation: Orchestrates the entire process of parsing documents into interconnected data structures.
  • Context preservation: Maintains the semantic weight of relationships extracted from dense technical documentation.

Where teams use it

Map corporate knowledge

Convert thousands of internal documents into a highly searchable, interconnected knowledge graph.

Enhance RAG systems

Provide language models with structured relationship data to improve generation accuracy drastically.

Analyze complex networks

Identify hidden connections within large datasets of legal or scientific documentation automatically.

Automate data entry

Extract specific entities from dense reports without relying on manual human review.

Getting started: https://github.com/Graphify-Labs/graphify

README

v8 branch

Graphify

Graphify-Labs%2Fgraphify | Trendshift

PyPI CI License: Apache-2.0 Downloads Docs Graphify Cloud Discord YouTube LinkedIn YC S26

Start free, no card required →
Cut agent token spend by 80%. Graphify Cloud is always-on memory that governs your agents, keeps code quality high, and proves correctness with formal verification.

Type /graphify in your AI coding assistant and it maps your entire project (code, docs, PDFs, images, videos) into a knowledge graph you can query instead of grepping through files.

  • Code maps for free, fully local. Code is parsed with tree-sitter AST: deterministic, no LLM, nothing leaves your machine. (Docs, PDFs, images and video use your assistant's model, or a configured API key, for a semantic pass.)
  • Every edge is explained. Each connection is tagged EXTRACTED (explicit in the source) or INFERRED (resolved by graphify), so you can tell what was read directly from what was inferred.
  • Not a vector index. No embeddings, no vector store: a real graph you traverse. Ask a question, trace the path between two things, or explain one concept.

Note

Want this always-on? Graphify Cloud keeps the graph live across your entire SDLC: monorepo and cross-repo support, formal verification, and code review with a bird's-eye view of your SDLC, plus connectors for Sentry, Jira, and more so incidents and tickets sit in the same graph as your code. Start free, no card required.

graphify's interactive graph.html showing the FastAPI codebase as a force-directed knowledge graph with a legend of detected communities

The FastAPI codebase mapped by graphify. Every node is a concept, colors are detected communities, and the whole thing is clickable in graph.html.

Get started (30 seconds). Needs Python 3.10+ and uv (or pipx):

uv tool install graphifyy      # install the CLI (or: pipx install graphifyy)
graphify install               # detects your assistant and registers the skill

Then, in your AI assistant:

/graphify .

That's it. You get three files:

graphify-out/
├── graph.html       open in any browser: click nodes, filter, search
├── GRAPH_REPORT.md  the highlights: key concepts, surprising connections, suggested questions
└── graph.json       the full graph: query it anytime without re-reading your files

The persisted graph includes graph.schema_version so integrations can detect incompatible format changes, plus graph.graphify_version identifying the Graphify release that produced it.

One install, any assistant, any OS. Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, and 20+ more, on macOS, Linux, and Windows: pick your platform.


See it in action

graphify path query: a terminal asks for the shortest path between FastAPI and ModelField, and the answer lights up hop by hop across the knowledge graph

Once the graph is built you query it instead of reading files. Real output, graphify run on the FastAPI codebase shown above:

$ graphify explain "APIRouter"
Node: APIRouter
  Source:    routing.py L2210
  Community: 2
  Degree:    47

Connections (47):
  --> RequestValidationError [uses] [INFERRED]
  --> Dependant [uses] [INFERRED]
  --> .get() [method] [EXTRACTED]
  <-- __init__.py [imports] [EXTRACTED]
  ...

$ graphify path "FastAPI" "ModelField"
Shortest path (3 hops):
  FastAPI --uses--> DefaultPlaceholder <--references-- get_request_handler() --references--> ModelField

Every edge carries a confidence tag (EXTRACTED = explicit in the source, INFERRED = derived by resolution), so you can tell what was read directly from what was inferred. graphify query "<question>" returns a scoped subgraph for a plain-language question, and graphify path A B traces how any two things connect, ending with the path's overall confidence: that of its weakest hop.


What it does

What you get out of the box:

Capability What you get
God nodes The most-connected concepts, so you see what everything flows through
Communities The graph split into subsystems (Leiden), with LLM-free labels
Cross-file links calls / imports / inherits / mixes_in resolved across ~40 languages via tree-sitter AST
Query, path, explain Ask a question, trace the path between two things, or explain one concept, all against graph.json
Rationale + doc refs # NOTE: / # WHY: comments and ADR/RFC citations become first-class nodes linked to the code
Beyond code Docs, PDFs, images, and video/audio all map into the same graph
Local-first Code is parsed locally with tree-sitter (no LLM, nothing leaves your machine); only the semantic pass over docs/media calls a backend, and only if you configure one

Tip

Running this across many repos or a monorepo? Graphify Cloud does it continuously and cuts agent token spend by 80%, with cross-repo links, SDLC-wide code review, formal verification, and Sentry/Jira connectors. Start free, no card required →


Benchmarks: 0.497 recall@10, 0 LLM credits

Benchmark Metric graphify Field
LOCOMO (n=300) recall@10 0.497 mem0 0.048, supermemory 0.149
LOCOMO (n=300) QA accuracy 45.3% supermemory 49.7%, mem0 27.3%
LongMemEval-S (n=50) QA accuracy 76% tied with dense RAG
ERPNext cross-tool (n=6) key-fact coverage 82.0% grep/read baseline 70.8%
Graph build LLM credits 0 per-token for most systems

Every system ran on the same harness with the same model and budgets, scored by a judge blind-validated against a second judge (90.6% agreement, Cohen's kappa 0.81). Full per-system tables, the code-intelligence result, and reproduction commands: BENCHMARKS.md.


Documentation

Full guides and reference live at docs.graphify.com:


Prerequisites

Requirement Minimum Check Install
Python 3.10+ python --version python.org
uv (recommended) any uv --version curl -LsSf https://astral.sh/uv/install.sh | sh
pipx (alternative) any pipx --version pip install pipx

macOS quick install (Homebrew):

brew install [email protected] uv

Windows quick install:

winget install astral-sh.uv

Ubuntu/Debian:

# uv manages its own Python, so this is the only step you need:
curl -LsSf https://astral.sh/uv/install.sh | sh
# or use the system Python with pipx:
sudo apt install python3 python3-pip pipx

Install

Important

Official package: The PyPI package is graphifyy (double-y). Other graphify* packages on PyPI are not affiliated. The CLI command is still graphify.

The official source repository is Graphify-Labs/graphify.

The two-command quickstart is at the top of this README. This section covers the install methods, project-scoped installs, and every supported platform.

Install methods (pick one):

uv tool install graphifyy   # recommended, isolated env (if 'graphify' isn't found after, run: uv tool update-shell)
pipx install graphifyy      # alternative
pip install graphifyy       # may need PATH setup, see Troubleshooting below

Then run graphify install once. It detects which assistant you run and registers the skill, so there is no per-assistant setup. Open your AI assistant and type /graphify .

To install the assistant skill into the current repository instead of your user profile, add --project:

graphify install --project
graphify install --project --platform codex

Project-scoped installs write under the current directory, for example .claude/skills/graphify/SKILL.md or .agents/skills/graphify/SKILL.md (plus a references/ sidecar the skill loads on demand), and print a git add hint for files that can be committed. Per-platform commands that support project-scoped installs accept the same flag, for example graphify claude install --project or graphify codex install --project.

Tip

Hitting command not found, a pip-on-Mac/Windows issue, PowerShell quoting, uvx usage, git-hook PATH quirks, or strict mode? See Installation and Troubleshooting.

Pick your platform (20+ assistants, click to expand)
Platform Install command
Claude Code (Linux/Mac) graphify install
Claude Code (Windows) graphify install (auto-detected) or graphify install --platform windows
CodeBuddy graphify install --platform codebuddy
Codex graphify install --platform codex
OpenCode graphify install --platform opencode
Kilo Code graphify install --platform kilo
GitHub Copilot CLI graphify install --platform copilot
VS Code Copilot Chat graphify vscode install
Aider graphify install --platform aider
OpenClaw graphify install --platform claw
Factory Droid graphify install --platform droid
Trae graphify install --platform trae
Trae CN graphify install --platform trae-cn
Gemini CLI graphify install --platform gemini
Hermes graphify install --platform hermes
Kimi Code graphify install --platform kimi
Amp graphify amp install
Agent Skills (cross-framework) graphify install --platform agents (alias --platform skills)
Kiro IDE/CLI graphify kiro install
Pi coding agent graphify install --platform pi, plus graphify pi guard install for the native guard
Cursor graphify cursor install
Devin CLI graphify devin install
Google Antigravity graphify antigravity install
Google Antigravity (Windows) graphify antigravity install (auto-detected on Windows)

Codex users also need multi_agent = true under [features] in ~/.codex/config.toml for parallel extraction. CodeBuddy uses the same Agent tool and PreToolUse hook mechanism as Claude Code. Factory Droid uses the Task tool for parallel subagent dispatch. OpenClaw and Aider use sequential extraction (parallel agent support is still early on those platforms). Trae uses the Agent tool for parallel subagent dispatch and does not support PreToolUse hooks, so AGENTS.md is the always-on mechanism.

--platform agents (alias --platform skills) targets the generic cross-framework Agent-Skills locations: the spec's user-global ~/.agents/skills/ (read by npx skills and spec-compliant frameworks) for a global install, and ./.agents/skills/ for a project (--project) install. The bare graphify install stays single-platform (Claude Code) by design: use the named agents platform when you want the skill discoverable by any framework that reads .agents/skills.

Claude Code's graphify install --project --strict makes Read and dedicated Grep share one denial per session unless a recent graph query has oriented the agent (default 30 minutes). A Grep over a directory needs no indexed-file match; a Grep pinned to a single file is denied only when the graph indexes that file, as with Read. External and graph-output Grep targets produce neither a deny nor a nudge, in soft mode as well as strict mode, matching Read's scope. A graph marked needs_update never triggers a Grep denial. Bash searches and Glob stay advisory. GRAPHIFY_HOOK_STRICT=1 enables the policy without reinstalling; GRAPHIFY_HOOK_STRICT=0 disables it even when installed with --strict. Existing strict installs need a reinstall to add the search hook's --strict flag, or the environment override. Soft nudges are capped per session (GRAPHIFY_HOOK_NUDGE_CAP, default 5). After a context compaction, a SessionStart hook (matcher compact) resets that budget, the subagents' budgets and the strict denial, since the compacted context no longer holds the earlier nudges.

Pi has no PreToolUse hook, so graphify pi guard install registers a native Pi extension (via Pi's own pi install <package directory>) that runs the installed graphify hook-guard before Pi's read, grep, find and search-style bash calls. Fresh/stale graph decisions and the GRAPHIFY_HOOK_STRICT=1 once-per-session denial shared by indexed Read and dedicated Grep come from that same policy, so Pi matches Claude Code's hook behavior; Bash and file listing remain advisory. Guidance arrives as a <system-reminder source="graphify"> steering message. It needs Pi 0.58.4 or newer: earlier versions let a steering message skip the rest of a parallel tool-call batch. The package ships inside the Graphify installation, so install Graphify persistently (uv tool install graphifyy or pipx install graphifyy, not uvx), restart Pi after installing or upgrading, and remove it with graphify pi guard uninstall. Only local file targets are inspected; the hook needs graphify on an absolute PATH entry outside the project, is bounded to a two-second, 256 KiB-in/64 KiB-out call, and fails open. The same package also loads in Oh My Pi: omp plugin install "$(graphify pi guard path)". The registered path contains the Python version and venv, so re-run graphify pi guard install after changing either, and remove the old entry with pi remove <old path>.

Codex uses $graphify instead of /graphify.

Optional extras (install only what you need)
Extra What it adds Install
pdf PDF extraction uv tool install "graphifyy[pdf]"
office .docx and .xlsx support uv tool install "graphifyy[office]"
google Google Sheets rendering uv tool install "graphifyy[google]"
video Video/audio transcription (faster-whisper + yt-dlp) uv tool install "graphifyy[video]"
mcp MCP stdio server uv tool install "graphifyy[mcp]"
watch Auto-rebuild on file changes (graphify watch) uv tool install "graphifyy[watch]"
neo4j Neo4j push support uv tool install "graphifyy[neo4j]"
falkordb FalkorDB push support uv tool install "graphifyy[falkordb]"
svg SVG graph export uv tool install "graphifyy[svg]"
leiden Leiden community detection (graspologic on Python < 3.13; native backend on 3.13+) uv tool install "graphifyy[leiden]"
ollama Ollama local inference uv tool install "graphifyy[ollama]"
openai OpenAI / OpenAI-compatible APIs uv tool install "graphifyy[openai]"
gemini Google Gemini API uv tool install "graphifyy[gemini]"
anthropic Anthropic Claude API (--backend claude, uses ANTHROPIC_API_KEY) uv tool install "graphifyy[anthropic]"
bedrock AWS Bedrock (uses IAM, no API key) uv tool install "graphifyy[bedrock]"
azure Azure OpenAI Service (--backend azure, uses AZURE_OPENAI_API_KEY + AZURE_OPENAI_ENDPOINT) uv tool install "graphifyy[openai]"
sql SQL schema extraction uv tool install "graphifyy[sql]"
postgres Live PostgreSQL introspection (--postgres DSN) uv tool install "graphifyy[postgres]"
dm BYOND DreamMaker .dm/.dme AST extraction (may need a C compiler + python3-dev if no wheel matches your platform) uv tool install "graphifyy[dm]"
terraform Terraform / HCL .tf/.tfvars/.hcl AST extraction uv tool install "graphifyy[terraform]"
pascal Pascal / Delphi .pas/.dpr/.dpk/.inc AST extraction (more accurate calls/inherits edges; falls back to a regex extractor when absent) uv tool install "graphifyy[pascal]"
ocaml OCaml .ml/.mli AST extraction uv tool install "graphifyy[ocaml]"
commonlisp Common Lisp .lisp/.cl/.lsp/.asd AST extraction uv tool install "graphifyy[commonlisp]"
robot Robot Framework .robot/.resource extraction (suites, test cases, keywords, keyword-call and resource/library import edges) uv tool install "graphifyy[robot]"
chinese Chinese query segmentation (jieba) uv tool install "graphifyy[chinese]"
all Everything above uv tool install "graphifyy[all]"

Make your assistant always use the graph

Run this once in your project after building a graph:

Run graphify <platform> install once in your project, for example graphify claude install or graphify codex install (or graphify install --platform <name>).

This writes a small config file that tells your assistant to consult the knowledge graph for codebase questions, preferring scoped queries like graphify query "<question>" over reading the full report or grepping raw files.

  • Hook platforms (Claude Code, Gemini CLI): a hook fires automatically before search-style tool calls (and, on Claude Code, before reading source files one by one via the Read/Glob tools, or via cat, head, tail, sed -n and similar readers in Bash) and nudges your assistant toward the graph path.
  • Instruction-file platforms (Codex, OpenCode, Cursor, etc.): persistent instruction files (AGENTS.md, .cursor/rules/, etc.) provide the same query-first guidance.

GRAPH_REPORT.md is still available for broad architecture review.

Exactly which files each platform writes (CodeBuddy's CODEBUDDY.md + PreToolUse hooks, Codex's AGENTS.md, Kilo's native .kilo plugin, Cursor's alwaysApply rule, and so on) is covered in Always-on setup.

To remove graphify from all platforms at once: graphify uninstall (add --purge to also delete graphify-out/). Or use the per-platform command (e.g. graphify claude uninstall).

CLI skills or MCP instructions?

The instructions installed by graphify install and those supplied with a Graphify MCP connection describe different ways to query a graph:

Setup Guidance to use Query access
Local CLI and installed assistant skill The platform instructions written by graphify install Run graphify query, graphify path, and graphify explain against the local graph (graphify-out/ by default).
Connected Graphify MCP server The connection's instructions and the tools listed by that server Call the listed MCP tools against the graph served by that connection. Tool names and descriptions come from the server.

Both encourage scoped graph queries before broad source searches. Choose the instructions that match the tools your assistant can actually access; neither block establishes a universal precedence rule for your assistant's instruction files. If you use both integrations, identify which graph each queries and choose a primary query path instead of copying two unconditional instruction blocks into AGENTS.md.

graphify install installs the local assistant integration; it does not establish an MCP connection. An MCP client does not need to run local CLI queries to use its connected server. A locally hosted server still needs its own Graphify installation and graph, while a hosted connection may serve a graph that is not present in the client's working directory. If the expected tools are missing, check the relevant CLI installation or MCP connection rather than treating the other setup's instructions as interchangeable.


What's in the report

GRAPH_REPORT.md summarizes the god nodes, communities, and key paths for broad architecture review. How the graph is built and what it contains: How graphify works.


What files it handles: ~40 languages

graphify parses ~40 programming languages locally with tree-sitter AST, and maps docs, PDFs, images, and audio/video through an optional semantic pass. Full list: Supported inputs.


Common commands

/graphify .                        # build graph for current folder
/graphify ./docs --update          # re-extract only changed files
/graphify . --cluster-only         # rerun clustering without re-extracting
/graphify . --cluster-only --resolution 1.5      # more granular communities
/graphify . --cluster-only --exclude-hubs 99     # suppress utility super-hubs from god-node rankings
/graphify . --no-viz               # skip the HTML, just the report + JSON
/graphify . --wiki                 # build a markdown wiki from the graph
graphify export callflow-html      # Mermaid architecture/call-flow HTML (auto-regenerates on every git commit if hook is installed)

/graphify query "what connects auth to the database?"
/graphify path "UserService" "DatabasePool"
/graphify explain "RateLimiter"

/graphify add https://arxiv.org/abs/1706.03762   # fetch a paper and add it
/graphify add <youtube-url>                       # transcribe and add a video

graphify hook install              # auto-rebuild on commit + branch checkout (run `graphify update .` after `git pull`: see "Recommended workflow" below)
graphify merge-graphs a.json b.json              # combine two graphs

graphify prs                       # PR dashboard: CI state, review status, worktree mapping
graphify prs 42                    # deep dive on PR #42 with graph impact
graphify prs --triage              # AI ranks your review queue (uses whatever backend is configured)
graphify prs --conflicts           # PRs sharing graph communities: merge-order risk

See the full command reference below.


Labeling and rendering limits

  • --batch-size: 100 communities per labeling call by default, sized for a ~16k-token context (~150 tokens/community). Use --batch-size 40 for an 8k window. Context overflow is not split-retried; failed batches keep hub-derived names.
  • --missing-only: label --missing-only keeps existing labels and names only unnamed / Community N entries. Use label (full relabel) to refresh names after the community set changes.
  • .graphify_labels.json.sig: records the community membership signature; labels survive a re-cluster only while it matches.
  • export html: 5,000-node default; above it graphify renders an aggregated community view. Use --node-limit N. GRAPHIFY_VIZ_NODE_LIMIT / .graphifyrc viz_node_limit=N apply to cluster-only, update, watch, and hooks, not export html.
  • Leiden fallback: without the leiden extra, clustering silently uses networkx Louvain. Switching later reshuffles every community, so plan a full relabel.

Ignoring files

graphify honors .gitignore and supports --exclude patterns and a project .graphifyignore. Details: Configuration.

graphify extract reports paths skipped by ignore rules, with up to three sorted examples relative to the scan root. Each pruned directory counts once; its contents are not enumerated. Default noise directories such as node_modules are excluded from this summary. If source is missing, review the ignore rules. --no-gitignore bypasses VCS ignore rules only; .graphifyignore and --exclude remain effective.

Project configuration

Create a .graphifyrc in the scan root for settings that belong to the project rather than to one run. One key=value per line; lines beginning with # are comments.

Ambiguous extensions. Some extensions mean different languages in different projects: .inc is PHP on pfSense, Pascal in a Delphi tree, SQL or assembly elsewhere; .h is C or C++; .m is Objective-C or MATLAB. graphify has to pick one global default, and when it picks wrong the file does not fail: it parses as the wrong language and yields a handful of incidental nodes, so the graph looks populated while the real symbols are missing. Declare what the extension means in your repo:

# .graphifyrc
# A language name:
language.inc=php
# Or an extension graphify already knows:
language.tpl=.ts
# Baked into the git hooks (see Team setup):
viz_node_limit=0

The declaration flows through classification, extractor selection, grammar and resolution, imports, graphify watch, and the AST cache (a file re-parsed under a different language never reuses the old entry), and the same .graphifyrc is read by extract, update, the hooks, the MCP server, and the /graphify skill. A typo is reported once on stderr and the scan continues with the defaults. How declarations interact with caching, incremental rebuilds, and import resolution: Configuration.

Query defaults. Set query_budget to a positive integer and query_depth to an integer from 1 to 6:

query_budget=4000
query_depth=3

For graphify query, explicit --budget N / --budget=N and --depth N / --depth=N override these settings independently. Without a project setting or explicit option, the defaults remain budget 2000 and depth 2. These keys do not change the MCP server's defaults.

Settings come from the project owning the selected --graph, even when the command runs from another directory. An existing absolute directory in the graph's sibling .graphify_root marker identifies that project. Otherwise a matching relative GRAPHIFY_OUT suffix identifies it; absolute, empty, traversal-containing or nonmatching output paths fall back to the graph file's directory. Relative markers are ignored.

The query command always reads that project's .graphifyrc. An invalid recognized setting or an unreadable file produces one stderr warning and discards all project settings for that query; explicit options still apply. The settings parser stays strict for its other callers. Existing explicit budget values retain their behavior; persisted query_budget values must be positive.


Team setup

Commit or share the graph so your whole team queries the same context, and review pull requests with graph context. See Share context with your team and Review pull requests.


Using the graph directly

Beyond your AI assistant, query graph.json straight from the CLI with graphify query, graphify path, and graphify explain. A name that matches several nodes is refused with the candidates listed rather than guessed. Scripts can read the outcome from the exit code: 0 an answer, 3 an ambiguous name, 4 no matching node. See Ask better graph questions and the query reference.


Environment variables

Backends, API keys, hook behavior, and tuning are controlled by environment variables. Full table: Configuration.

  • Claude API prompt caching: GRAPHIFY_CLAUDE_PROMPT_CACHE controls system-prompt caching for --backend claude. Unset or blank keeps caching enabled; 1, true, yes, or on explicitly enables it, and 0, false, no, or off disables it (case-insensitive, surrounding whitespace ignored). Invalid values raise an error before sending a request. For example, run GRAPHIFY_CLAUDE_PROMPT_CACHE=0 graphify extract . --backend claude when an Anthropic-compatible endpoint rejects cache_control. Disabling sends the original plain-text system prompt. The setting applies equally to official Anthropic and custom ANTHROPIC_BASE_URL / ANTHROPIC_MODEL endpoints, including deep mode; it does not affect Bedrock, Claude CLI, or Graphify's local extraction cache. Enabling requests caching but cannot guarantee cache hits: the endpoint/model must support it and the prompt must meet its minimum length. Unsupported caching errors are not silently retried without caching.
  • Claude CLI model: GRAPHIFY_CLAUDE_CLI_MODEL overrides the model for the claude-cli backend (default: Opus). haiku or sonnet are usually enough for community naming; the semantic extraction pass benefits from a larger model.

Privacy

  • Code files: processed locally via tree-sitter. Nothing leaves your machine. A code-only corpus requires no API key: graphify extract runs fully offline. On a mixed repo, add --code-only to index just the code and skip the docs/PDFs/images that would otherwise need an LLM.
  • Video / audio: transcribed locally with faster-whisper. Nothing leaves your machine.
  • Docs, PDFs, images: sent to your AI assistant for semantic extraction (via the /graphify skill, using whatever model your IDE session runs). Headless graphify extract requires GEMINI_API_KEY / GOOGLE_API_KEY (Gemini), MOONSHOT_API_KEY (Kimi), ANTHROPIC_API_KEY (Claude), OPENAI_API_KEY (OpenAI), DEEPSEEK_API_KEY (DeepSeek), a running Ollama instance (OLLAMA_BASE_URL), AWS credentials via the standard provider chain (Bedrock - no API key needed, uses IAM), or the claude CLI binary (Claude Code - no API key needed, uses your Claude subscription). The --dedup-llm flag uses the same key.
  • Data residency: graphify extract auto-detects which provider to use based on which API key is set (priority: Gemini → Kimi → Claude → OpenAI → DeepSeek → Azure → Bedrock → Ollama). When it auto-detects, it prints the exact environment variable that chose the provider, so a run is never a surprise. To choose explicitly, pass --backend, or set GRAPHIFY_BACKEND=<name>; set GRAPHIFY_BACKEND=none to disable all LLM backends (semantic extraction and the claude -p labeling fallback) and keep a code-only graph. For code with data-residency requirements, use GRAPHIFY_BACKEND=ollama / --backend ollama (fully local). Kimi (MOONSHOT_API_KEY) routes to Moonshot AI servers in China.
  • No telemetry, no usage tracking, no analytics.
  • Query logging: every graphify query, graphify path, graphify explain, and MCP query_graph call is logged to ~/.cache/graphify-queries.log in JSON Lines format (timestamp, question, corpus, nodes returned, duration). Full subgraph responses are not stored by default. Set GRAPHIFY_QUERY_LOG_DISABLE=1 to opt out, or GRAPHIFY_QUERY_LOG=/dev/null to silence without disabling the code path.

Troubleshooting

Common install and extraction issues and their fixes: Troubleshooting.


Full command reference

Every command and flag, with examples: CLI reference.


Learn more


Graphify Cloud

Graphify Cloud is the always-on layer built on top of graphify. Instead of a graph you rebuild on demand per folder, it keeps one live graph across your entire software development lifecycle:

  • 80% fewer tokens: always-on memory means your agents stop re-reading and re-explaining the codebase every session.
  • Monorepo and cross-repo: one connected graph across every service and repository, not a graph per folder.
  • Formal verification: check architectural and dependency invariants against the live graph.
  • Code review with a bird's-eye view of your SDLC: see how a change ripples across the whole system before you merge.
  • SDLC connectors: pull in Sentry, Jira, and more, so incidents, tickets, and code live in one graph.
  • Always-on: updates continuously in the background across code, docs, and meetings.

Start free, no card required →


Contributing

Contributions are welcome. See CONTRIBUTING.md for the development setup, the test and CI-parity commands, the git workflow, and what makes a strong contribution (worked examples and extraction bug reports are the most useful). Architecture and how to add a language: ARCHITECTURE.md.

New here? Say hi on Discord or in GitHub Discussions.


Contributors

graphify contributors

Made with contrib.rocks.


Translations

The README is available in 32 languages. Use the language switcher at the top of this file to read it in yours, or browse docs/translations/. To improve a translation or add a new one, open a pull request against the matching file there.


Building on graphify

Building something in the graphify ecosystem? That is encouraged. If your project uses "graphify" in its name (for example graphify-dashboard or graphify-action), please add a short note to your README clarifying that it is community-built and not affiliated with or endorsed by Graphify Labs. "graphify" and the graphify logo are marks of Graphify Labs; please do not use them in a way that implies official status.


Community and links

Website Discord X YouTube Sponsor The Memory Layer

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

254 total
  1. graphify 0.9.108v0.9.108Nov 12, 2026180 downloads

    - Fix: **csharp** a member call on a receiver typed by a lowercase, underscore-prefixed or keyword-like type (`_Pair`, `pair`, a field or primary-constructor parameter so typed) now binds, and a static call like `pair.Create()` resolves; namespace and unknown receivers still fail closed. Classic extension-method calls on `bool`/`char?` receivers also bind (#5174, thanks @JensD-git). - Fix: **java** a call through a class-qualified static field (`Service.INSTANCE.get()`, and a chain `Service.INSTANCE.other().m()`) resolves via that field's declared type; a local or parameter that shadows the class name keeps that binding, and an instance field accessed as `Type.field` is not treated as static (#5149, thanks @MaxWang007). - Fix: **sql** a routine body preserves comma joins (`FROM a, b`) so every table is read, and keeps a `@dblink` suffix as a distinct remote node instead of pointing the edge at a local same-named table (#5169, thanks @mohitdixit02). - Fix: **sql** an unparsed derived table's alias (`FROM (SELECT ...) q` where the subquery fails to parse) is no longer mis-read as a table node; a real table after the subquery is unaffected (#5147, thanks @Yi-111-a). - Fix: **path** `g

  2. graphify 0.9.107v0.9.107Nov 11, 2026192 downloads

    - Fix: **cpp** a folded parameterless member declaration (`bar()`) records its implementation in `definition_file` as a path anchored to the same root as `source_file`, instead of a `../`-walk relative to the cache/out root. The zero-argument reconciliation added in 0.9.106 stored the internal `_cpp_source_key` proof form, which `_norm_source_file` cannot re-anchor (it only relativizes absolute paths), so an out-of-tree corpus got a mangled `definition_file`. The sibling decl/def merge already stored the raw `source_file` for this reason; both paths now agree. The include-path proof still uses the key form. - Fix: **llm** a slice whose timeout or context overflow is recognised and given up on (it cannot be split further, or the retry depth is exhausted) now marks its file partial, so a document whose tail slice timed out is no longer cached and stamped complete from its other slices; it is re-queued on the next run while sibling files' results are kept (#5099, thanks @khrisshie). - Fix: **php** a route path scan stops at the closure's own argument, so `$app->get('/users', function () { ... })` keeps `GET /users` instead of reading a trailing string argument after the closure as the

  3. graphify 0.9.106v0.9.106Nov 10, 2026162 downloads

    ## graphify 0.9.106 - Fix: **install** `requires-python` is capped to `>=3.10,<3.15`, so `uv tool install graphifyy` (and pip) on a fresh machine no longer selects Python 3.15 — for which `tree-sitter` has no wheel — and then fails with a source build that needs a C compiler (`No such file or directory: 'cc'`). uv now picks a wheel-having interpreter (3.14) by default, with no `--python` flag and no compiler needed. The Ubuntu/Debian README line that asked for `python3.12` (absent on Debian 12 and Ubuntu 22.04) is replaced with the uv installer or a plain `python3`/pipx line (#5134). - Fix: **cpp** a plain class/struct forward declaration folds into its unique exactly-qualified definition when one file reaches the other through unconditional exact quoted includes, and a parameterless member declaration folds into its proven out-of-line definition by matching return type and qualifiers; overloads, templates, conditional declarations and unproven includes stay separate (#5117, thanks @xRedLeader). - Fix: **cpp** a member call resolves through a scoped type alias (`using Alias = ns::Type;`) and through inherited fields/methods, and a forward-declared pointee type is completed at the

  4. graphify 0.9.105v0.9.105Nov 9, 2026198 downloads

    ## graphify 0.9.105 - Fix: **watch** ignored directories (`node_modules`, `.git`, build output) are pruned from the Linux watch tree, so a large project no longer registers tens of thousands of wasted inotify watches and risks `ENOSPC`; the non-Linux recursive watcher is unchanged and still fires on every real change (#5074, #5091, thanks @Deepjyoti-Sarmah). - Fix: **cpp** a member-call chain routed through class fields declared in other headers (`client.actions->Execute()`, with value `.`, raw-pointer `->` and single-arg `unique_ptr`/`shared_ptr` receivers) resolves to the field type's member across the include set, gated to a unique type and member and fail-closed otherwise; a typed local whose class is in another repo is parked for the cross-repo merge (#5098, thanks @xRedLeader). - Fix: **markdown** a code span naming an uppercase `\`-namespace class (`\Foo\Bar`, `App\API`) or a type-qualified method call (`Type::member()`) is kept as a symbol mention instead of being dropped, while a non-call `Type::CONST`/`Type::class` stays dropped (#5093, thanks @Adityakk9031). - Fix: **ts/js** a call through a destructured CommonJS barrel require (`const { Thing } = require('./barrel')` w

  5. graphify 0.9.104v0.9.104Nov 8, 2026223 downloads

    ## graphify 0.9.104 - Security: **skill** the `/graphify` runbook no longer substitutes the scan path into Python code. Every generated code block (detect, AST and semantic extraction, build, diagnose, label, manifest, and `--update`) now reads the resolved scan root from the trusted `graphify-out/.graphify_root` sidecar that Step 1 writes through a quoted heredoc, instead of pasting the agent-supplied path into a string literal. A directory whose name carried a quote or `$(...)` could previously break out of `Path('INPUT_PATH')` and run as code; it is now read as inert data. Covers the assembled hosts and the Aider/Devin monoliths (#4762, thanks @danikdanik). - Fix: **solidity** a call on a receiver of a contract or interface type (`IERC20 token; token.transfer()`, `IERC20(a).transfer()`, `token().balanceOf()`) binds by name and arity through that type's linearization to the type's own declaration, instead of producing no edge; gated to a single visible contract/interface and fail-closed on an unknown or ambiguous type (#5060, thanks @rohit-jsfreaky). - Fix: **solidity** a call attached by a `using A for T` directive (`using SafeCast for uint256; x.toUint48()`) binds to the libra

Code frequency

additions and deletions
+72.3K-72.3KWeek of 2026-03-29: +18,822 linesWeek of 2026-03-29: -2,680 linesWeek of 2026-04-05: +28,799 linesWeek of 2026-04-05: -6,806 linesWeek of 2026-04-12: +4,208 linesWeek of 2026-04-12: -1,120 linesWeek of 2026-04-19: +10,618 linesWeek of 2026-04-19: -6,752 linesWeek of 2026-04-26: +8,139 linesWeek of 2026-04-26: -3,157 linesWeek of 2026-05-03: +11,281 linesWeek of 2026-05-03: -1,889 linesWeek of 2026-05-10: +72,298 linesWeek of 2026-05-10: -4,968 linesWeek of 2026-05-17: +11,883 linesWeek of 2026-05-17: -538 linesWeek of 2026-05-24: +16,835 linesWeek of 2026-05-24: -884 linesWeek of 2026-05-31: +45,682 linesWeek of 2026-05-31: -9,844 linesWeek of 2026-06-07: +9,337 linesWeek of 2026-06-07: -864 linesWeek of 2026-06-14: +8,796 linesWeek of 2026-06-14: -1,947 linesWeek of 2026-06-21: +12,136 linesWeek of 2026-06-21: -1,221 linesWeek of 2026-06-28: +14,540 linesWeek of 2026-06-28: -1,638 linesWeek of 2026-07-05: +26,068 linesWeek of 2026-07-05: -18,927 linesWeek of 2026-07-12: +11,563 linesWeek of 2026-07-12: -872 linesWeek of 2026-07-19: +8,623 linesWeek of 2026-07-19: -717 linesWeek of 2026-07-26: +8,903 linesWeek of 2026-07-26: -922 linesWeek of 2026-08-02: +7,493 linesWeek of 2026-08-02: -697 linesWeek of 2026-08-09: +9,846 linesWeek of 2026-08-09: -622 linesWeek of 2026-08-16: +10,264 linesWeek of 2026-08-16: -461 linesWeek of 2026-08-23: +7,397 linesWeek of 2026-08-23: -437 linesWeek of 2026-08-30: +7,113 linesWeek of 2026-08-30: -389 linesWeek of 2026-09-06: +8,332 linesWeek of 2026-09-06: -786 linesWeek of 2026-09-13: +7,632 linesWeek of 2026-09-13: -277 linesWeek of 2026-09-20: +11,025 linesWeek of 2026-09-20: -1,133 linesWeek of 2026-09-27: +14,192 linesWeek of 2026-09-27: -1,227 linesWeek of 2026-10-04: +31,939 linesWeek of 2026-10-04: -5,169 linesWeek of 2026-10-11: +25,489 linesWeek of 2026-10-11: -5,748 linesWeek of 2026-10-18: +12,820 linesWeek of 2026-10-18: -2,909 linesWeek of 2026-10-25: +16,789 linesWeek of 2026-10-25: -1,383 linesWeek of 2026-11-01: +16,101 linesWeek of 2026-11-01: -1,946 linesWeek of 2026-11-08: +10,961 linesWeek of 2026-11-08: -1,697 linesMar 29, 2026Nov 8, 2026
+525.9K lines added, -90.6K removed over the last year.

Commits per week

last 52 weeks
1760Week of 2025-11-16: 0 commitsWeek of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 0 commitsWeek of 2026-03-15: 0 commitsWeek of 2026-03-22: 0 commitsWeek of 2026-03-29: 10 commitsWeek of 2026-04-05: 120 commitsWeek of 2026-04-12: 39 commitsWeek of 2026-04-19: 37 commitsWeek of 2026-04-26: 74 commitsWeek of 2026-05-03: 100 commitsWeek of 2026-05-10: 69 commitsWeek of 2026-05-17: 45 commitsWeek of 2026-05-24: 59 commitsWeek of 2026-05-31: 67 commitsWeek of 2026-06-07: 67 commitsWeek of 2026-06-14: 41 commitsWeek of 2026-06-21: 63 commitsWeek of 2026-06-28: 128 commitsWeek of 2026-07-05: 94 commitsWeek of 2026-07-12: 106 commitsWeek of 2026-07-19: 90 commitsWeek of 2026-07-26: 72 commitsWeek of 2026-08-02: 15 commitsWeek of 2026-08-09: 92 commitsWeek of 2026-08-16: 87 commitsWeek of 2026-08-23: 76 commitsWeek of 2026-08-30: 58 commitsWeek of 2026-09-06: 95 commitsWeek of 2026-09-13: 107 commitsWeek of 2026-09-20: 126 commitsWeek of 2026-09-27: 118 commitsWeek of 2026-10-04: 176 commitsWeek of 2026-10-11: 152 commitsWeek of 2026-10-18: 139 commitsWeek of 2026-10-25: 170 commitsWeek of 2026-11-01: 165 commitsWeek of 2026-11-08: 102 commitsNov 16, 2025Nov 8, 2026
3K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 30 commitsSun 1:00 — 10 commitsSun 2:00 — 10 commitsSun 3:00 — 1 commitsSun 4:00 — 3 commitsSun 5:00 — 3 commitsSun 6:00 — 4 commitsSun 7:00 — 0 commitsSun 8:00 — 2 commitsSun 9:00 — 6 commitsSun 10:00 — 17 commitsSun 11:00 — 19 commitsSun 12:00 — 13 commitsSun 13:00 — 16 commitsSun 14:00 — 21 commitsSun 15:00 — 35 commitsSun 16:00 — 20 commitsSun 17:00 — 18 commitsSun 18:00 — 35 commitsSun 19:00 — 22 commitsSun 20:00 — 23 commitsSun 21:00 — 8 commitsSun 22:00 — 18 commitsSun 23:00 — 16 commitsMon 0:00 — 16 commitsMon 1:00 — 12 commitsMon 2:00 — 8 commitsMon 3:00 — 4 commitsMon 4:00 — 0 commitsMon 5:00 — 0 commitsMon 6:00 — 5 commitsMon 7:00 — 3 commitsMon 8:00 — 7 commitsMon 9:00 — 16 commitsMon 10:00 — 20 commitsMon 11:00 — 20 commitsMon 12:00 — 23 commitsMon 13:00 — 30 commitsMon 14:00 — 48 commitsMon 15:00 — 34 commitsMon 16:00 — 43 commitsMon 17:00 — 27 commitsMon 18:00 — 37 commitsMon 19:00 — 23 commitsMon 20:00 — 27 commitsMon 21:00 — 24 commitsMon 22:00 — 42 commitsMon 23:00 — 16 commitsTue 0:00 — 19 commitsTue 1:00 — 10 commitsTue 2:00 — 12 commitsTue 3:00 — 13 commitsTue 4:00 — 11 commitsTue 5:00 — 2 commitsTue 6:00 — 3 commitsTue 7:00 — 3 commitsTue 8:00 — 7 commitsTue 9:00 — 17 commitsTue 10:00 — 25 commitsTue 11:00 — 32 commitsTue 12:00 — 35 commitsTue 13:00 — 29 commitsTue 14:00 — 26 commitsTue 15:00 — 27 commitsTue 16:00 — 22 commitsTue 17:00 — 9 commitsTue 18:00 — 25 commitsTue 19:00 — 11 commitsTue 20:00 — 21 commitsTue 21:00 — 29 commitsTue 22:00 — 41 commitsTue 23:00 — 26 commitsWed 0:00 — 29 commitsWed 1:00 — 16 commitsWed 2:00 — 11 commitsWed 3:00 — 2 commitsWed 4:00 — 4 commitsWed 5:00 — 4 commitsWed 6:00 — 2 commitsWed 7:00 — 3 commitsWed 8:00 — 5 commitsWed 9:00 — 18 commitsWed 10:00 — 11 commitsWed 11:00 — 20 commitsWed 12:00 — 23 commitsWed 13:00 — 29 commitsWed 14:00 — 30 commitsWed 15:00 — 37 commitsWed 16:00 — 19 commitsWed 17:00 — 20 commitsWed 18:00 — 10 commitsWed 19:00 — 31 commitsWed 20:00 — 36 commitsWed 21:00 — 10 commitsWed 22:00 — 26 commitsWed 23:00 — 48 commitsThu 0:00 — 27 commitsThu 1:00 — 21 commitsThu 2:00 — 14 commitsThu 3:00 — 6 commitsThu 4:00 — 5 commitsThu 5:00 — 0 commitsThu 6:00 — 1 commitsThu 7:00 — 2 commitsThu 8:00 — 13 commitsThu 9:00 — 18 commitsThu 10:00 — 15 commitsThu 11:00 — 26 commitsThu 12:00 — 19 commitsThu 13:00 — 26 commitsThu 14:00 — 31 commitsThu 15:00 — 22 commitsThu 16:00 — 16 commitsThu 17:00 — 21 commitsThu 18:00 — 24 commitsThu 19:00 — 14 commitsThu 20:00 — 17 commitsThu 21:00 — 13 commitsThu 22:00 — 18 commitsThu 23:00 — 33 commitsFri 0:00 — 21 commitsFri 1:00 — 16 commitsFri 2:00 — 7 commitsFri 3:00 — 3 commitsFri 4:00 — 3 commitsFri 5:00 — 2 commitsFri 6:00 — 2 commitsFri 7:00 — 3 commitsFri 8:00 — 4 commitsFri 9:00 — 8 commitsFri 10:00 — 21 commitsFri 11:00 — 12 commitsFri 12:00 — 11 commitsFri 13:00 — 17 commitsFri 14:00 — 22 commitsFri 15:00 — 37 commitsFri 16:00 — 40 commitsFri 17:00 — 19 commitsFri 18:00 — 32 commitsFri 19:00 — 18 commitsFri 20:00 — 19 commitsFri 21:00 — 27 commitsFri 22:00 — 34 commitsFri 23:00 — 41 commitsSat 0:00 — 13 commitsSat 1:00 — 19 commitsSat 2:00 — 4 commitsSat 3:00 — 3 commitsSat 4:00 — 8 commitsSat 5:00 — 2 commitsSat 6:00 — 5 commitsSat 7:00 — 0 commitsSat 8:00 — 4 commitsSat 9:00 — 14 commitsSat 10:00 — 12 commitsSat 11:00 — 11 commitsSat 12:00 — 12 commitsSat 13:00 — 18 commitsSat 14:00 — 31 commitsSat 15:00 — 11 commitsSat 16:00 — 33 commitsSat 17:00 — 22 commitsSat 18:00 — 20 commitsSat 19:00 — 27 commitsSat 20:00 — 17 commitsSat 21:00 — 38 commitsSat 22:00 — 38 commitsSat 23:00 — 43 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Oct 29, 2026weekly#7+7,268
Oct 28, 2026weekly#7+7,268
Oct 27, 2026weekly#5+7,183
Oct 26, 2026weekly#5+6,903
Oct 25, 2026weekly#12+6,868
Oct 24, 2026daily#4+1,408
Oct 23, 2026daily#4+1,408
Oct 22, 2026daily#4+1,433
Oct 21, 2026daily#5+802
Jul 27, 2026daily#11+4
Jul 26, 2026daily#9+4
Jul 24, 2026daily#8+5
Jul 21, 2026daily#22+3
Jul 19, 2026daily#9+7
Jul 18, 2026daily#13+5
  • public-apis/public-apis

    A collective list of free APIs

    500.5K stars · Python

  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • donnemartin/system-design-primer

    Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

    378.7K stars · Python

  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    322.9K stars · Shell

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    307.9K stars · JavaScript