ruvnet/rufloPublic

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

AI summary: A streamlined, visual workflow automation engine for integrating cloud services and APIs.

Stars
82.1K
+298 today
Forks
9.7K
Watchers
478
Open issues
290
Open PRs
269
Contributors
~104
Commits
10.6K
Branches
1.1K
Views (30d)
17

TypeScriptMITCreated Jun 2, 2025Last push 1d agoLatest release v3.79.0+558 stars this week+3.9K this month

Quick answers

What is ruflo?
A streamlined, visual workflow automation engine for integrating cloud services and APIs.
What does ruflo do?
Ruflo is an open-source workflow automation platform that allows users to connect various cloud applications and APIs using a visual, drag-and-drop interface. It processes events asynchronously, enabling complex data transformations and conditional logic between different interconnected services. The system is designed to be highly extensible, allowing developers to create custom nodes for proprietary internal APIs. It can be self-hosted, ensuring data privacy and compliance for enterprise use cases. By abstracting API communication, it empowers non-engineers to build powerful automated workflows.
Who is ruflo for?
Operations teams, business analysts, and developers looking to automate repetitive tasks. It is ideal for organizations that require a powerful, self-hosted alternative to commercial automation tools.
How do I get started with ruflo?
docker compose up -d
How popular is ruflo on GitHub?
ruvnet/ruflo has 82,121 stars and 9,694 forks on GitHub, and gained 558 stars in the last 7 days.
What license does ruflo use?
ruvnet/ruflo is released under the MIT license.

Star history

since Jul 29, 2026
025K50K75KJul 2026Sep 2026Oct 2026Nov 2026
82.1K stars as of Nov 20, 2026. Measured daily since Jul 29, 2026; GitHub no longer exposes earlier star timestamps.

Update history

6 recorded
  • Nov 20, 2026New release v3.79.0 (previously v3.72.2).
  • Nov 8, 2026New release v3.72.2 (previously v3.63.5).
  • Oct 27, 2026New release v3.63.5 (previously v3.57.0).
  • Oct 18, 2026New release v3.57.0 (previously v3.56.1).
  • Oct 9, 2026New release v3.56.1 (previously v3.46.1).
  • Oct 4, 2026Previously tracked as ruvnet/claude-flow; its 1 daily snapshot and 1 trending appearance were merged into this profile. Stars: 66,483 on 2026-07-29 under the old name, 73,758 on 2026-10-03 (+7,275).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 3 commits2025-11-25: 25 commits2025-11-26: 4 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 4 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 2 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 12 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: 326 commits2026-01-08: 538 commits2026-01-09: 58 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 248 commits2026-01-13: 416 commits2026-01-14: 356 commits2026-01-15: 370 commits2026-01-16: 28 commits2026-01-17: 204 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 16 commits2026-01-21: 36 commits2026-01-22: 28 commits2026-01-23: 64 commits2026-01-24: 52 commits2026-01-25: 16 commits2026-01-26: 172 commits2026-01-27: 56 commits2026-01-28: 48 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 52 commits2026-02-02: 340 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 878 commits2026-02-08: 700 commits2026-02-09: 192 commits2026-02-10: 472 commits2026-02-11: 52 commits2026-02-12: 12 commits2026-02-13: 4 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 6 commits2026-02-17: 10 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: 6 commits2026-02-27: 16 commits2026-02-28: 18 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 23 commits2026-03-06: 2 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 2 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: 3 commits2026-03-17: 19 commits2026-03-18: 2 commits2026-03-19: 4 commits2026-03-20: 1 commit2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 15 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: 7 commits2026-04-03: 0 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 41 commits2026-04-07: 3 commits2026-04-08: 5 commits2026-04-09: 0 commits2026-04-10: 0 commits2026-04-11: 1 commit2026-04-12: 0 commits2026-04-13: 0 commits2026-04-14: 0 commits2026-04-15: 0 commits2026-04-16: 0 commits2026-04-17: 0 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 0 commits2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 0 commits2026-04-24: 0 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 14 commits2026-04-28: 11 commits2026-04-29: 10 commits2026-04-30: 15 commits2026-05-01: 18 commits2026-05-02: 1 commit2026-05-03: 36 commits2026-05-04: 42 commits2026-05-05: 31 commits2026-05-06: 25 commits2026-05-07: 4 commits2026-05-08: 25 commits2026-05-09: 23 commits2026-05-10: 7 commits2026-05-11: 6 commits2026-05-12: 8 commits2026-05-13: 11 commits2026-05-14: 28 commits2026-05-15: 1 commit2026-05-16: 5 commits2026-05-17: 0 commits2026-05-18: 23 commits2026-05-19: 46 commits2026-05-20: 13 commits2026-05-21: 35 commits2026-05-22: 2 commits2026-05-23: 7 commits2026-05-24: 7 commits2026-05-25: 10 commits2026-05-26: 3 commits2026-05-27: 6 commits2026-05-28: 7 commits2026-05-29: 16 commits2026-05-30: 18 commits2026-05-31: 2 commits2026-06-01: 1 commit2026-06-02: 10 commits2026-06-03: 0 commits2026-06-04: 2 commits2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 8 commits2026-06-09: 6 commits2026-06-10: 4 commits2026-06-11: 4 commits2026-06-12: 15 commits2026-06-13: 3 commits2026-06-14: 0 commits2026-06-15: 7 commits2026-06-16: 97 commits2026-06-17: 73 commits2026-06-18: 5 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 18 commits2026-06-23: 6 commits2026-06-24: 0 commits2026-06-25: 15 commits2026-06-26: 122 commits2026-06-27: 21 commits2026-06-28: 0 commits2026-06-29: 9 commits2026-06-30: 0 commits2026-07-01: 3 commits2026-07-02: 0 commits2026-07-03: 17 commits2026-07-04: 13 commits2026-07-05: 9 commits2026-07-06: 1 commit2026-07-07: 5 commits2026-07-08: 0 commits2026-07-09: 4 commits2026-07-10: 0 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 11 commits2026-07-14: 19 commits2026-07-15: 8 commits2026-07-16: 18 commits2026-07-17: 11 commits2026-07-18: 10 commits2026-07-19: 0 commits2026-07-20: 6 commits2026-07-21: 0 commits2026-07-22: 0 commits2026-07-23: 0 commits2026-07-24: 0 commits2026-07-25: 0 commits2026-07-26: 24 commits2026-07-27: 9 commits2026-07-28: 7 commits2026-07-29: 20 commits2026-07-30: 11 commits2026-07-31: 4 commits2026-08-01: 0 commits2026-08-02: 0 commits2026-08-03: 0 commits2026-08-04: 0 commits2026-08-05: 0 commits2026-08-06: 0 commits2026-08-07: 0 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 4 commits2026-08-11: 18 commits2026-08-12: 25 commits2026-08-13: 9 commits2026-08-14: 11 commits2026-08-15: 6 commits2026-08-16: 0 commits2026-08-17: 0 commits2026-08-18: 0 commits2026-08-19: 3 commits2026-08-20: 5 commits2026-08-21: 13 commits2026-08-22: 7 commits2026-08-23: 0 commits2026-08-24: 2 commits2026-08-25: 0 commits2026-08-26: 0 commits2026-08-27: 1 commit2026-08-28: 0 commits2026-08-29: 0 commits2026-08-30: 3 commits2026-08-31: 0 commits2026-09-01: 2 commits2026-09-02: 2 commits2026-09-03: 0 commits2026-09-04: 0 commits2026-09-05: 7 commits2026-09-06: 0 commits2026-09-07: 6 commits2026-09-08: 2 commits2026-09-09: 9 commits2026-09-10: 22 commits2026-09-11: 11 commits2026-09-12: 6 commits2026-09-13: 1 commit2026-09-14: 28 commits2026-09-15: 5 commits2026-09-16: 42 commits2026-09-17: 3 commits2026-09-18: 0 commits2026-09-19: 9 commits2026-09-20: 17 commits2026-09-21: 22 commits2026-09-22: 0 commits2026-09-23: 4 commits2026-09-24: 11 commits2026-09-25: 23 commits2026-09-26: 91 commits2026-09-27: 119 commits2026-09-28: 29 commits2026-09-29: 17 commits2026-09-30: 54 commits2026-10-01: 85 commits2026-10-02: 124 commits2026-10-03: 84 commits2026-10-04: 227 commits2026-10-05: 223 commits2026-10-06: 136 commits2026-10-07: 99 commits2026-10-08: 98 commits2026-10-09: 97 commits2026-10-10: 178 commits2026-10-11: 188 commits2026-10-12: 133 commits2026-10-13: 27 commits2026-10-14: 111 commits2026-10-15: 1 commit2026-10-16: 0 commits2026-10-17: 31 commits2026-10-18: 37 commits2026-10-19: 77 commits2026-10-20: 55 commits2026-10-21: 45 commits2026-10-22: 62 commits2026-10-23: 49 commits2026-10-24: 29 commits2026-10-25: 16 commits2026-10-26: 32 commits2026-10-27: 23 commits2026-10-28: 23 commits2026-10-29: 34 commits2026-10-30: 12 commits2026-10-31: 17 commits2026-11-01: 29 commits2026-11-02: 11 commits2026-11-03: 5 commits2026-11-04: 98 commits2026-11-05: 138 commits2026-11-06: 48 commits2026-11-07: 5 commits2026-11-08: 37 commits2026-11-09: 144 commits2026-11-10: 88 commits2026-11-11: 30 commits2026-11-12: 20 commits2026-11-13: 4 commits2026-11-14: 1 commit2026-11-15: 0 commits2026-11-16: 15 commits2026-11-17: 49 commits2026-11-18: 15 commits2026-11-19: 95 commits2026-11-20: 0 commits2026-11-21: 0 commits
10,954 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Landmark project

    82,121 stars

  • Very active

    10,954 commits in 52 weeks

  • Community-driven

    ~104 contributors

  • Well documented

    High community health score

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

  • Repeat trending

    48 trending appearances

  • Top 10% tracked

    Rank 115 of 1243

What ruflo does

Ruflo is an open-source workflow automation platform that allows users to connect various cloud applications and APIs using a visual, drag-and-drop interface. It processes events asynchronously, enabling complex data transformations and conditional logic between different interconnected services. The system is designed to be highly extensible, allowing developers to create custom nodes for proprietary internal APIs. It can be self-hosted, ensuring data privacy and compliance for enterprise use cases. By abstracting API communication, it empowers non-engineers to build powerful automated workflows.

Operations teams, business analysts, and developers looking to automate repetitive tasks. It is ideal for organizations that require a powerful, self-hosted alternative to commercial automation tools.

  • Visual workflow builder: Provides a drag-and-drop interface for designing complex logic without writing code.
  • Extensive integrations: Supports connecting to hundreds of popular SaaS applications and databases.
  • Custom node creation: Allows developers to write custom JavaScript to integrate proprietary systems.
  • Self-hosting capabilities: Enables deployment on internal servers to maintain strict data privacy.
  • Conditional logic: Supports branching, loops, and comprehensive error handling within the automated workflows.

Where teams use it

Business process automation

Operations teams use it to automatically sync customer data between a CRM and a billing system.

Alerting and monitoring

Engineers configure workflows to send Slack notifications when a database metric exceeds a threshold.

Data transformation

Analysts create pipelines to extract data from an API, reformat it, and load it into a data warehouse.

Webhook handling

Developers utilize it to catch external webhooks and trigger internal serverless functions.

Getting started: docker compose up -d

README

main branch

Ruflo animated neon sign

ruPro workspace tour showing project agents, provider terminals, evidence review and business dashboards

Explore ruPro Try the interactive demo

An agent meta-harness for Claude Code and Codex.

npm version (ruflo) MIT License Star on GitHub Follow @rUv on X

Claude Flow lineage: first commit June 2, 2025 by rUv; inspect the evidence 120.95 million observed npm download events since October 1, 2025, across 429 packages. Verified November 16, 2026. Lower bound; not unique users or lifetime downloads.
Claude Code plugin View Claude plugin listing in the Claude plugin directory Codex plugin ChatGPT plugin: RuFlo Federation

Run your first task

Run this in your project folder:

npx ruflo@latest init

Then open Claude Code in the same folder and give it a real task, for example:

Use a ruflo swarm to review this repo: find the riskiest module, write tests for it, and summarise what you changed.

init adds ruflo's agents, hooks, memory and MCP server to the project, and Claude Code picks them up on its next start. Codex and other MCP clients work too: point them at npx -y ruflo@latest mcp start.

Check the result. Ask the agent to name the module it chose, show the test it added, and report the test command and result. Review the diff in your project.

Looping recording of the ruflo console: overview, swarm view and missions in a sample project

First task walkthrough · Inspect a run in Mission Control · Other ways to install

Other ways to install

There are two different install paths with very different surface areas. Pick based on what you need (#1744):

Claude Code Plugin CLI install (npx ruflo init)
What it gives you Slash commands + a few skills + agent definitions per-plugin Full Ruflo loop — 98 agents, 60+ commands, 30 skills, MCP server, hooks, daemon
Files in your workspace Zero .claude/, .claude-flow/, CLAUDE.md, helpers, settings
MCP server registered Only if ruflo-core is installed (it ships its own .mcp.json) — most other plugins don't Yes
Hooks installed No Yes
Best for Try a single plugin's commands without committing to the full install Production use — everything works as documented

Claude Code plugins only. This route installs core tools, the visual console and runtime mods, with no files added to your project. It needs Claude Code 2.1.287 or later. Run inside Claude Code:

/plugin marketplace add ruvnet/ruflo
/plugin install ruflo-core@ruflo
/plugin install ruflo-console@ruflo
/plugin install ruflo-mods@ruflo
/reload-plugins
/ruflo

From a terminal, on Claude Code 2.1.292 or later: claude plugin install ruflo-core@ruflo --marketplace ruvnet/ruflo. Mods run with your account's permissions, so review their code before installing.

Codex or another MCP client, without project setup. Configure the command npx with the arguments ["-y", "ruflo@latest", "mcp", "start"]. To set up a project interactively, run npx ruflo@latest init wizard.

Plain terminal. The console also runs on its own, without Claude Code: npx ruflo tui. Add --plain to print one frame for scripts. See the terminal UI guide.

Looping recording of the optional ruflo terminal UI with its pictures: Overview in the Classic BBS look, the Orbital look with its moving globe, and the Swarm graph, in a sample project

ruflo-core registers its own MCP server. Its tools use the mcp__plugin_ruflo-core_ruflo__ prefix.

CLI Install

macOS / Linux / WSL / Git-Bash:

# One-line install (POSIX shells only — see Windows note below)
curl -fsSL https://cdn.jsdelivr.net/gh/ruvnet/ruflo@main/scripts/install.sh | bash

All platforms (including native Windows PowerShell / cmd):

# Interactive setup wizard — runs identically on every platform
npx ruflo@latest init wizard

# Quick non-interactive init
# npx ruflo@latest init

# Or install globally
npm install -g ruflo@latest

💡 Windows users: the curl ... | bash form needs a POSIX shell (Git-Bash, WSL, MSYS). The npx ruflo@latest init wizard line works natively in PowerShell and cmd. If you hit an 'bash' is not recognized error, use the npx line instead — both end up running the same init flow.

MCP Server

# Add Ruflo as an MCP server in Claude Code
claude mcp add claude-flow -- npx ruflo@latest mcp start

For static inspection of local applications and binaries, see the ruRE plugin guide.


Grok Build: npx ruflo init --grok writes the project host surface (.grok/, the team bus, and the operator guide) and nothing outside the project; add --dry-run to preview. Setup, the spawn_subagent contract, the optional status row, and what to re-check when Grok updates: the Grok operator guide.

Mission Control

Mission Control console overview

Open /ruflo in Claude Code to monitor agent work, inspect a run, or give Claude permission to operate the console.

If you use the console, open the agent’s log and compare its actions with the diff and test result from your first task.

Task What you can do
Monitor work Track workflows, agents, models, token use, and cost. Workflow demo with sample data
Inspect a run Search logs and results, triage failures, replay a run, and compare outcomes.
Customize the console Preview Orbital, switch among six palettes, save a theme, or import its JSON. 38 second renderer replay · Theme Studio guide
Control Claude’s access Choose a permission level and approval mode in Settings → Claude control. Review each action in the live log. Permission details

Install and open the console

Use Claude Code 2.1.287 or later. Review mods before installing them because they run with your account’s permissions.

/plugin marketplace add ruvnet/ruflo
/plugin install ruflo-console@ruflo
/plugin install ruflo-mods@ruflo
/reload-plugins

Open /plugin to check the active mods, then /ruflo to launch the console. For a project initialized through the CLI, run npx ruflo init and restart Claude Code before opening /ruflo.

Console mods and catalog
Mod Purpose
ruflo-console Opens the console beside Claude Code.
ruflo-mods Routes prompts and enforces policy in process.
ruflo-swarm Adds a pane showing the swarm.
ruflo-ruos Adds the ruOS status segment.

Open /ruflo market to inspect plugins, mods, and skills. The catalog asks for confirmation before installing, enabling, disabling, or updating an item.

Create a mission with Claude

The default is read + ask. Available levels are read, write, manage, and full, with ask or auto approval. Actions above the selected level are refused. Network, spending, and destructive actions require confirmation even in auto.

  1. In Settings → Claude control, select write + ask.
  2. Ask Claude, “Create a mission to add a dark mode toggle. Show me the mission and its status.”
  3. Confirm the pending creation request. Check Missions for the goal and Overview for the action log. This verifies that the mission was created.
  4. Select Take back control, then ask Claude to take another console action. The console should refuse it until you restore access.

Watch the recorded Claude Haiku session to see mission creation, page navigation, a refused swarm stop, and control being taken back. The recording uses write + auto. Step 1 uses ask so you can approve creation yourself. Recorded test findings · Reproduction script

Choose your next capability

Agent teamsPersistent memory
Learning loopsSecurity controls
Plugin marketplaceModels and routing
Capability counts and implementation details
Capability Description
100+ Agents Specialized agents for coding, testing, security, docs, architecture
Comms Layer Zero-trust federation — agents across machines/orgs discover, authenticate, and exchange work securely
Swarm Coordination Hierarchical, mesh, and adaptive topologies with consensus
Self-Learning SONA neural patterns, ReasoningBank, trajectory learning
Vector Memory HNSW-indexed AgentDB — measured ~1.9x faster at N=20k, ~3.2x–4.7x at N=5k vs brute force (recall@10 ~0.99); ANN wins above the crossover, ties/loses at small N. See audit + scripts/benchmark-intelligence.mjs
Background Workers 12 auto-triggered workers (audit, optimize, testgaps, etc.)
Plugin Marketplace 48 native Claude Code plugins + 14 in-tree npm plugins
Multi-Provider Claude, GPT, Gemini, Cohere, Ollama with smart routing
Security AIDefence, input validation, CVE remediation, path traversal prevention
Agent Federation Cross-installation agent collaboration with zero-trust security
MetaHarness Audit your AI agent setup before you ship. Grade readiness (1-100), scan tool configs for security issues, snapshot the whole project to catch regressions over time, and find templates that match your repo. ruflo eject turns a ruflo project into a standalone agent toolkit with its own name. Full guide.
🔌 All 48 plugins (plus 3 external)
Core & Orchestration
Plugin What it does
ruflo-core Foundation — server, health checks, plugin discovery
ruflo-swarm Coordinate multiple agents as a team
ruflo-autopilot Let agents run autonomously in a loop
ruflo-loop-workers Schedule background tasks on a timer
ruflo-workflows Reusable multi-step task templates
ruflo-federation Agents on different machines collaborate securely
ruflo-console Cockpit inside Claude Code, and the /ruflo command for ruflo mods
ruflo-mods In-process Claude Code mod — routing, learning signals, and policy checks
ruflo-ai-team Tenant-isolated team that divides work and returns evidence
ruflo-agntcy AGNTCY/Outshift transport and intent-scoped tool authorization
ruflo-bbs-federation AgentBBS rooms so agents on different hosts can coordinate
ruflo-chatgpt-federation ChatGPT federation publisher with its own signing keys
ruflo-x-gateway Signed federation messages, channels, and work claims
ruflo-business-pods Business-domain pod templates and a dry-run tick runner
Memory & Knowledge
Plugin What it does
ruflo-agentdb Fast vector database for agent memory
ruflo-rag-memory Smart retrieval — hybrid search, graph hops, diversity ranking
ruflo-rvf Save and restore agent memory across sessions
ruflo-ruvector ruvector — GPU-accelerated search, Graph RAG, 103 tools
ruflo-knowledge-graph Build and traverse entity relationship maps
Intelligence & Learning
Plugin What it does
ruflo-intelligence Agents learn from past successes and get smarter
ruflo-graph-intelligence Sublinear graph reasoning — PageRank, delta updates, complexity-aware execution (ADR-123)
ruflo-daa Dynamic agent behavior and cognitive patterns
ruflo-ruvllm Run local LLMs (Ollama, etc.) with smart routing
ruflo-goals Break big goals into plans and track progress
ruflo-deepseek-harness Agents, commands, and skills for DeepSeek-backed workflows
Code Quality & Testing
Plugin What it does
ruflo-testgen Find missing tests and generate them automatically
ruflo-browser Automate browser testing with Playwright
ruflo-jujutsu Analyze git diffs, score risk, suggest reviewers
ruflo-rure Static analysis of a local JS/Electron app you are authorized to study, with file and line evidence
ruflo-docs Generate and maintain documentation automatically
agentic-qe-fleet External, maintained by Agentic QE: 11 QE agents, test generation, coverage, chaos and TDD skills, the agentic-qe MCP server, and a guard for AQE learning data (/plugin install agentic-qe-fleet@ruflo). Install it from one marketplace only, agentic-qe or ruflo: enabled from both, its mod and commands load twice
agentdb External, maintained in ruvnet/agentdb: agentdb's own MCP server (pinned [email protected]: hybrid keyword + vector search, opt-in cross-encoder rerank), a memory-specialist agent, vector-memory / learning / diagnostics skills, /agentdb-status, and a guard that keeps secrets out of memory and refuses delete/reset unless allowed (/plugin install agentdb@ruflo). Use ruflo-agentdb instead if you want AgentDB through ruflo's server; the two can coexist. Install it from one marketplace only, agentdb or ruflo
agentic-flow External, maintained in ruvnet/agentic-flow: the agentic-flow MCP server (pinned [email protected], readonly profile by default, nothing pre-approved), ReasoningBank and model-router agents, routing / learning / autopilot skills, /agentic-flow-status, and a guard on agentic_flow_agent (/plugin install agentic-flow@ruflo). Install it from one marketplace only, agentic-flow or ruflo
Security & Compliance
Plugin What it does
ruflo-security-audit Scan for vulnerabilities and CVEs
ruflo-aidefence Block prompt injection, detect PII, safety scanning
ruflo-protector Optional watchdog for unattended agents — learn, notify, or enforce
Architecture & Methodology
Plugin What it does
ruflo-adr Track architecture decisions with a living record
ruflo-ddd Scaffold domain-driven design — contexts, aggregates, events
ruflo-sparc Guided 5-phase development methodology with quality gates
ruflo-metaharness Grade your agent setup, scan tool configs for security risks, and track changes over time (guide)
ruflo-arena Competitive ruliology — pit agent strategies against each other in tournaments, hill-climb and co-evolve the winners (ADR-147/148)
DevOps & Observability
Plugin What it does
ruflo-migrations Manage database schema changes safely
ruflo-observability Structured logs, traces, and metrics in one place
ruflo-cost-tracker Track token usage, set budgets, get cost alerts
ruflo-ruos Run swarm agents on your own ruOS cloud desktops
Extensibility
Plugin What it does
ruflo-agent Run agents — local WASM sandbox (rvagent) + Anthropic Claude Managed Agents (cloud), with opt-in bounded dynamic workflows, gated session controls and verified advisory learning
ruflo-plugin-creator Scaffold, validate, and publish your own plugins
Domain-Specific
Plugin What it does
ruflo-iot-cognitum IoT device management — trust scoring, anomaly detection, fleets
ruflo-neural-trader neural-trader — AI trading with 4 agents, backtesting, 112+ tools
ruflo-market-data Ingest market data, vectorize OHLCV, detect patterns
ruflo-music Compose and generate music through a Cognitum Music account

How Ruflo works

Agent = Model + Harness. The model writes; the harness gives it tools, memory, loops, sandboxes, and controls so it can actually work. Ruflo is the harness — the execution layer around Claude Code and Codex that adds 100+ specialized agents, coordinated swarms, self-learning memory, federated comms across machines, and enterprise security guardrails. So agents don't just run, they collaborate.

What can the next run reuse?

Recall, execute, evaluate, store, adapt and reuse: an illustrative agent learning cycle.

Useful trajectories and task feedback can inform future work. Results depend on the configured memory, learning components and quality of feedback. Learning plugin.

Watch the learning walkthrough · Local RVF search recipe

Conceptual learning loop. Local vector retrieval and contrastive updates can run without an LLM; embeddings and configured learning modules are still required. See the RuVector training integration and trajectory contrastive learning.

How do two teams exchange work?

Outbound agent, data filtering, signing and encryption, identity verification, input checks and receiving agent.

Slack gave teams channels. Federation gives agents the same thing — shared workspaces across trust boundaries, where agents on different machines, orgs, or cloud regions can discover each other, prove who they are, and collaborate on tasks.

The difference: some channels are trusted, some aren't. @claude-flow/plugin-agent-federation handles that automatically. Your agents join a federation, get verified via mTLS + ed25519, and start exchanging work — with PII stripped before anything leaves your node and every message auditable. Untrusted agents can still participate at lower privilege: they see discovery info, not your memory. As they prove reliable, trust upgrades. If they misbehave, they get downgraded instantly — no human in the loop required.

You don't configure handshakes or manage certificates. You federation init, federation join, and your agents start talking. The protocol handles identity, the PII pipeline handles data safety, and the audit trail handles compliance.

📘 Full user guide: docs/federation/ — setup, MCP tools, trust levels, circuit breaker, and the (opt-in) WireGuard mesh layer that ties packet-layer reachability to federation trust. ADR-111 deep-dive at docs/federation/phase7-mesh-bringup.md.

Federation capabilities
Capability How it works
🔒 Zero-trust federation Remote agents start untrusted. Identity proven via mTLS + ed25519 challenge-response. No API keys, no shared secrets.
🛡️ PII-gated data flow 14-type detection pipeline scans every outbound message. Per-trust-level policies: BLOCK, REDACT, HASH, or PASS. Adaptive calibration reduces false positives.
📊 Behavioral trust scoring Formula (0.4×success + 0.2×uptime + 0.2×threat + 0.2×integrity) continuously evaluates peers. Upgrades require history; downgrades are instant.
📋 Compliance built-in HIPAA, SOC2, GDPR audit trails as compliance modes. Every federation event produces a structured record searchable via HNSW.
🤝 9 MCP tools + 10 CLI commands Full lifecycle: federation_init, federation_send, federation_trust, federation_audit, and more.
Example: two teams sharing fraud signals without sharing customer data
# Team A: initialize federation and generate keypair
npx claude-flow@latest federation init

# Team A: join Team B's federation endpoint
npx claude-flow@latest federation join wss://team-b.example.com:8443

# Team A: send a task — PII is stripped automatically before it leaves
npx claude-flow@latest federation send --to team-b --type task-request \
  --message "Analyze transaction patterns for account anomalies"

# Team A: check peer trust levels and session health
npx claude-flow@latest federation status

See issue #1669 for the complete architecture, trust model, and implementation roadmap.

# Claude Code plugin
/plugin install ruflo-federation@ruflo

# Or via CLI
npx claude-flow@latest plugins install @claude-flow/plugin-agent-federation
Claude Code: With vs Without Ruflo
Capability Claude Code Alone + Ruflo
Agent Collaboration Isolated, no shared context Swarms with shared memory and consensus
Coordination Manual orchestration Queen-led hierarchy (Raft, Byzantine, Gossip)
Memory Session-only HNSW vector memory with sub-ms retrieval
Learning Static behavior SONA self-learning with pattern matching
Task Routing You decide Intelligent routing (89% accuracy)
Background Workers None 12 auto-triggered workers
LLM Providers Anthropic only 5 providers with failover
Security Standard CVE-hardened with AIDefence
Architecture overview
User --> Claude Code / CLI
          |
          v
    Orchestration Layer
    (MCP Server, Router, 27 Hooks)
          |
          v
    Swarm Coordination
    (Queen, Topology, Consensus)
          |
          v
    100+ Specialized Agents
    (coder, tester, reviewer, architect, security...)
          |
          v
    Memory & Learning
    (AgentDB, HNSW, SONA, ReasoningBank)
          |
          v
    LLM Providers
    (Claude, GPT, Gemini, Cohere, Ollama)

Explore the ecosystem

Project What it adds Get started
ruOS A desktop that connects to Claude or ChatGPT through MCP. Connect to https://ruos.cognitum.one/mcp
RuVector Local vector search and persistent context for agents. Run npx ruvector
Cognitum Edge infrastructure for ambient intelligence. Explore Cognitum One

See the ruOS desktop · Watch the RuVector overview · Ruvnet ecosystem

Documentation

Guides, architecture and verification

English · 简体中文

📖 RuFlo Explained — Build an AI Team That Plans, Remembers, Tests, and Improves A 14-chapter guide: from the basic idea to a first useful task, then memory, agent teams, plugins, cost and verification.

Doc When to read it
Status See what currently works — capability counts, test baselines, recent fixes, what's next. The is-it-ready doc.
User Guide Daily reference — every command, every config flag, every plugin. The how-do-I doc.
Compare frameworks Deciding between Ruflo, Claude Code built-in agents, CrewAI, LangGraph, or AutoGen. The which-one-for-me doc.
MetaHarness Guide How to grade your agent setup, scan tool configs for security, detect changes between runs, and eject a project into a standalone agent toolkit. The audit-my-setup doc.
Benchmarks v3.8.0 SOTA matrix vs LangGraph / AutoGen / CrewAI on darwin-arm64 + linux-x64. ruflo wins cold start, single turn, RSS by 1.3×–1953×. The is-it-fast doc.
Verification Cryptographically prove your installed bytes match the signed witness — ruflo verify. The trust-but-verify doc.
Team Gateway Checklist Before-merge gates, dual-mode handoff, memory namespace sharing, and witness manifest entry per merge. The safer-team-workflows doc.

Benchmark internals (for reproduction): sota-workload-spec.md · SOTA-PROGRESS.md · raw matrix JSON: darwin · linux

User Guide section index
Guide section Topics
Quick Start Installation, prerequisites, install profiles
Core Features MCP tools, agents, memory, neural learning
Intelligence & Learning Hooks, workers, SONA, model routing
Swarm & Coordination Topologies, consensus, hive mind
Security AIDefence, CVE remediation, validation
Ecosystem RuVector, agentic-flow, Flow Nexus
Configuration Environment variables, config schema
Plugin Marketplace Browse and install plugins
📖 Background — where the name comes from

Claude Flow is now Ruflo — named by rUv, who loves Rust, flow states, and building things that feel inevitable. The "Ru" is the rUv. The "flo" is working until 3am. Underneath, powered by Cognitum.One agentic architecture, running a supercharged Rust-based AI engine, embeddings, memory, and plugin system.

Support

Build with the Ruflo community

Resource Link
Documentation User Guide
Issues & Bugs GitHub Issues
Enterprise ruv.io
Community Agentics Foundation Discord
Powered by Cognitum.one

License

MIT - RuvNet

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

1,000 total
  1. ## 3.79.0: provenance-attested releases, pinned install output, Project Anatole on by default This is the first ruflo release published from CI with **SLSA provenance**. `@claude-flow/cli`, `claude-flow` and `ruflo` 3.79.0 each carry a SLSA v1 attestation built in `ruvnet/ruflo` by `stable-npm-release.yml`. `latest` moved only after the release gate confirmed that each attestation matches the verified archive's sha512 (ADR-545). ### Supply chain (ADR-545, #5048) - **CI-only publishing:** the release train now publishes only from GitHub Actions with `npm publish --provenance`, and only from `main`. The workflow rehearses by default (dry run), and publishing requires `dry_run=false`. - **Pinned `init` output:** `ruflo init` writes our packages at the CLI's own exact version (`npx -y [email protected] …`) instead of `@latest`. `--channel latest` keeps the old floating behaviour. - **`ruflo init repin` (or `init --repin`):** moves an existing project's `.claude/settings.json`, `.mcp.json`, CLAUDE.md and helpers onto the current version. It supports `--dry-run` and lists every changed line. - **`ruflo doctor -c provenance`:** checks that the pinned version has a SLSA attestation from `ruvn

  2. ## Fix - **SONA balanced mode returns current, exact matches** (#5044). Balanced mode served pattern matches from a cache keyed on a lossy embedding hash. That cache could return stale patterns after an update, or a near-duplicate query's results. It is removed: balanced mode now does an exact scan with bounded top-k selection, so its recall matches a full sort. Ships via `@claude-flow/neural` 3.1.1. ## Packages - `@claude-flow/cli`, `claude-flow`, `ruflo` 3.78.1 on `latest` - `@claude-flow/neural` 3.1.1 on `latest`

  3. Published: `@claude-flow/cli`, `claude-flow` and `ruflo` 3.78.0 on `latest`. The `@claude-flow/mcp` 3.1.8 and `@claude-flow/security` 3.0.8 standalone packages were also republished. It is a minor bump because `@claude-flow/neural` 3.1.0 and `@claude-flow/memory` 3.4.0 (#5041) add surface. ## Since 3.77.2 - Security: - #5032: authenticate `/ws` upgrades and compare tokens in constant time (`@claude-flow/shared` 3.0.10); - #4962: transport and WebSocket limits; - #5021: zod 4 migration; - #5039: guard every `.claude-flow` write and sign the companion helpers (integrates #4991); - #5037: show learned lessons only from a file this machine wrote (integrates #4854); - #3835: settings.json risk scanner on session-restore. - Dream cycle: - #5041: neural/memory fixes (integrates #4660, #4973, #4081, #3650, #4983, #5034, #5012); - #5004: `guidance_brain` coverage; - #4989: swarm consensus listener limits. `@claude-flow/swarm` is not republished, so this stays inert in the installed CLI. - Other: - #4822: memory lock ownership; - #4641: chat-ui; - #4995: `init --dry-run`; - #5040: MCP tool coverage (integrates #4840). ## Leaf packages - `mcp` 3.1.7 → 3.1.8 and `s

  4. Patch release on top of 3.77.1. ## Security - Managed-agent tools refuse sessions this project did not create. The ownership ledger moved out of the workspace (`~/.claude-flow/managed/`), and terminate checks the provider's environment id. (#4831, fixes #4751; thanks @MannXo) - The pre-bash root-delete guard reads `$(...)` substitutions and `${X:-/}` parameter defaults. (#4848 via #5024; thanks @MannXo) - Federation envelopes get a freshness check and replay guard. (#4849 via #5022) ## Fixes - The semantic router database stays under the memory root. (#4835) - Memory exits non-zero when a refused sql.js save loses writes. (#4839) - `init --dry-run` no longer performs a real init. (#4995) - Pins `@claude-flow/[email protected]`, which recovers HNSW entries the graph cannot reach. (#5018) - ruflo-mods 0.17.1: `claude plugin validate` passes on Claude Code 2.1.323+. (#5017) ## Install ``` npx [email protected] ``` `npm audit --omit=dev` on a fresh install matches 3.77.1 (7 high: zod, picomatch and agentic-flow chains, all tracked; zod 4 migration in #5021).

  5. ## 3.77.1 **Fix: AgentDB now honours the configured embedding model and dimension (#4984, #4985)** `memory_store` ignored `.claude-flow/embeddings.json` after #2305: the controller registry created AgentDB with only a `dbPath`, so a configured model and dimension were dropped and AgentDB fell back to all-MiniLM-L6-v2 at 384 dimensions. - `@claude-flow/memory` 3.3.3 forwards the configured dimension to AgentDB and installs the configured embedder, rejecting vectors of the wrong length. - The CLI memory bridge passes a local embedder when a non-default model is configured, and labels stored rows by the embedder that actually produced them. - Stores pinned to the default 384-dimension model are unchanged. Also merged: #4975 (quarantine a flaky browser suite on CI). Known: `no-metaharness-smoke` and the console `write-argv` test (#4978) were red on main before this release. Thanks to the reporter of #4984.

Code frequency

additions and deletions
+2M-2MWeek of 2025-11-02: +4,455 linesWeek of 2025-11-02: -6,746 linesWeek of 2025-11-09: +24,200 linesWeek of 2025-11-09: -1,188 linesWeek of 2025-11-16: +0 linesWeek of 2025-11-16: -0 linesWeek of 2025-11-23: +7,312 linesWeek of 2025-11-23: -4,200 linesWeek of 2025-11-30: +51 linesWeek of 2025-11-30: -6 linesWeek of 2025-12-07: +2,063 linesWeek of 2025-12-07: -1,542 linesWeek of 2025-12-14: +0 linesWeek of 2025-12-14: -0 linesWeek of 2025-12-21: +0 linesWeek of 2025-12-21: -0 linesWeek of 2025-12-28: +17,443 linesWeek of 2025-12-28: -56 linesWeek of 2026-01-04: +1,967,209 linesWeek of 2026-01-04: -1,744,652 linesWeek of 2026-01-11: +180,999 linesWeek of 2026-01-11: -10,660 linesWeek of 2026-01-18: +184,700 linesWeek of 2026-01-18: -1,993 linesWeek of 2026-01-25: +17,973 linesWeek of 2026-01-25: -587 linesWeek of 2026-02-01: +136,027 linesWeek of 2026-02-01: -10,867 linesWeek of 2026-02-08: +21,606 linesWeek of 2026-02-08: -7,735 linesWeek of 2026-02-15: +120 linesWeek of 2026-02-15: -70 linesWeek of 2026-02-22: +30,957 linesWeek of 2026-02-22: -5,190 linesWeek of 2026-03-01: +80,543 linesWeek of 2026-03-01: -4,345 linesWeek of 2026-03-08: +33 linesWeek of 2026-03-08: -33 linesWeek of 2026-03-15: +8,800 linesWeek of 2026-03-15: -929 linesWeek of 2026-03-22: +7,214 linesWeek of 2026-03-22: -5,379 linesWeek of 2026-03-29: +220 linesWeek of 2026-03-29: -100 linesWeek of 2026-04-05: +15,345 linesWeek of 2026-04-05: -4,054 linesWeek of 2026-04-12: +0 linesWeek of 2026-04-12: -0 linesWeek of 2026-04-19: +0 linesWeek of 2026-04-19: -0 linesWeek of 2026-04-26: +75,099 linesWeek of 2026-04-26: -20,450 linesWeek of 2026-05-03: +1,456,223 linesWeek of 2026-05-03: -1,430,071 linesWeek of 2026-05-10: +20,623 linesWeek of 2026-05-10: -1,052,051 linesWeek of 2026-05-17: +70,489 linesWeek of 2026-05-17: -17,179 linesWeek of 2026-05-24: +121,974 linesWeek of 2026-05-24: -4,436 linesWeek of 2026-05-31: +31,981 linesWeek of 2026-05-31: -524 linesWeek of 2026-06-07: +5,990 linesWeek of 2026-06-07: -753 linesWeek of 2026-06-14: +63,240 linesWeek of 2026-06-14: -3,567 linesWeek of 2026-06-21: +82,055 linesWeek of 2026-06-21: -8,469 linesWeek of 2026-06-28: +62,263 linesWeek of 2026-06-28: -33,477 linesWeek of 2026-07-05: +9,673 linesWeek of 2026-07-05: -1,136 linesWeek of 2026-07-12: +36,246 linesWeek of 2026-07-12: -7,519 linesWeek of 2026-07-19: +1,109 linesWeek of 2026-07-19: -97 linesWeek of 2026-07-26: +46,898 linesWeek of 2026-07-26: -14,091 linesWeek of 2026-08-02: +0 linesWeek of 2026-08-02: -0 linesWeek of 2026-08-09: +22,738 linesWeek of 2026-08-09: -6,042 linesWeek of 2026-08-16: +5,603 linesWeek of 2026-08-16: -371 linesWeek of 2026-08-23: +806 linesWeek of 2026-08-23: -21 linesWeek of 2026-08-30: +2,074 linesWeek of 2026-08-30: -220 linesWeek of 2026-09-06: +12,268 linesWeek of 2026-09-06: -841 linesWeek of 2026-09-13: +13,891 linesWeek of 2026-09-13: -1,161 linesWeek of 2026-09-20: +22,410 linesWeek of 2026-09-20: -1,586 linesWeek of 2026-09-27: +113,002 linesWeek of 2026-09-27: -8,046 linesWeek of 2026-10-04: +151,166 linesWeek of 2026-10-04: -41,148 linesWeek of 2026-10-11: +29,007 linesWeek of 2026-10-11: -4,881 linesWeek of 2026-10-18: +54,824 linesWeek of 2026-10-18: -4,194 linesWeek of 2026-10-25: +6,122 linesWeek of 2026-10-25: -2,801 linesNov 2, 2025Oct 25, 2026
+5.2M lines added, -4.5M removed over the last year.

Commits per week

last 52 weeks
16220Week of 2025-11-23: 36 commitsWeek of 2025-11-30: 2 commitsWeek of 2025-12-07: 12 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 922 commitsWeek of 2026-01-11: 1622 commitsWeek of 2026-01-18: 196 commitsWeek of 2026-01-25: 292 commitsWeek of 2026-02-01: 1270 commitsWeek of 2026-02-08: 1432 commitsWeek of 2026-02-15: 16 commitsWeek of 2026-02-22: 40 commitsWeek of 2026-03-01: 25 commitsWeek of 2026-03-08: 2 commitsWeek of 2026-03-15: 29 commitsWeek of 2026-03-22: 15 commitsWeek of 2026-03-29: 7 commitsWeek of 2026-04-05: 50 commitsWeek of 2026-04-12: 0 commitsWeek of 2026-04-19: 0 commitsWeek of 2026-04-26: 69 commitsWeek of 2026-05-03: 186 commitsWeek of 2026-05-10: 66 commitsWeek of 2026-05-17: 126 commitsWeek of 2026-05-24: 67 commitsWeek of 2026-05-31: 15 commitsWeek of 2026-06-07: 40 commitsWeek of 2026-06-14: 182 commitsWeek of 2026-06-21: 182 commitsWeek of 2026-06-28: 42 commitsWeek of 2026-07-05: 19 commitsWeek of 2026-07-12: 77 commitsWeek of 2026-07-19: 6 commitsWeek of 2026-07-26: 75 commitsWeek of 2026-08-02: 0 commitsWeek of 2026-08-09: 73 commitsWeek of 2026-08-16: 28 commitsWeek of 2026-08-23: 3 commitsWeek of 2026-08-30: 14 commitsWeek of 2026-09-06: 56 commitsWeek of 2026-09-13: 88 commitsWeek of 2026-09-20: 168 commitsWeek of 2026-09-27: 512 commitsWeek of 2026-10-04: 1058 commitsWeek of 2026-10-11: 491 commitsWeek of 2026-10-18: 354 commitsWeek of 2026-10-25: 157 commitsWeek of 2026-11-01: 334 commitsWeek of 2026-11-08: 324 commitsWeek of 2026-11-15: 174 commitsNov 23, 2025Nov 15, 2026
11K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 46 commitsSun 1:00 — 37 commitsSun 2:00 — 19 commitsSun 3:00 — 36 commitsSun 4:00 — 0 commitsSun 5:00 — 7 commitsSun 6:00 — 6 commitsSun 7:00 — 4 commitsSun 8:00 — 0 commitsSun 9:00 — 10 commitsSun 10:00 — 53 commitsSun 11:00 — 23 commitsSun 12:00 — 99 commitsSun 13:00 — 88 commitsSun 14:00 — 43 commitsSun 15:00 — 52 commitsSun 16:00 — 37 commitsSun 17:00 — 125 commitsSun 18:00 — 30 commitsSun 19:00 — 160 commitsSun 20:00 — 86 commitsSun 21:00 — 89 commitsSun 22:00 — 65 commitsSun 23:00 — 28 commitsMon 0:00 — 49 commitsMon 1:00 — 19 commitsMon 2:00 — 26 commitsMon 3:00 — 31 commitsMon 4:00 — 57 commitsMon 5:00 — 35 commitsMon 6:00 — 29 commitsMon 7:00 — 5 commitsMon 8:00 — 6 commitsMon 9:00 — 23 commitsMon 10:00 — 30 commitsMon 11:00 — 32 commitsMon 12:00 — 43 commitsMon 13:00 — 36 commitsMon 14:00 — 98 commitsMon 15:00 — 123 commitsMon 16:00 — 71 commitsMon 17:00 — 94 commitsMon 18:00 — 101 commitsMon 19:00 — 123 commitsMon 20:00 — 146 commitsMon 21:00 — 132 commitsMon 22:00 — 113 commitsMon 23:00 — 66 commitsTue 0:00 — 60 commitsTue 1:00 — 98 commitsTue 2:00 — 133 commitsTue 3:00 — 105 commitsTue 4:00 — 14 commitsTue 5:00 — 7 commitsTue 6:00 — 13 commitsTue 7:00 — 9 commitsTue 8:00 — 10 commitsTue 9:00 — 17 commitsTue 10:00 — 25 commitsTue 11:00 — 25 commitsTue 12:00 — 78 commitsTue 13:00 — 59 commitsTue 14:00 — 109 commitsTue 15:00 — 169 commitsTue 16:00 — 185 commitsTue 17:00 — 114 commitsTue 18:00 — 236 commitsTue 19:00 — 213 commitsTue 20:00 — 86 commitsTue 21:00 — 49 commitsTue 22:00 — 68 commitsTue 23:00 — 32 commitsWed 0:00 — 42 commitsWed 1:00 — 164 commitsWed 2:00 — 85 commitsWed 3:00 — 68 commitsWed 4:00 — 80 commitsWed 5:00 — 82 commitsWed 6:00 — 16 commitsWed 7:00 — 10 commitsWed 8:00 — 11 commitsWed 9:00 — 26 commitsWed 10:00 — 46 commitsWed 11:00 — 58 commitsWed 12:00 — 94 commitsWed 13:00 — 138 commitsWed 14:00 — 150 commitsWed 15:00 — 83 commitsWed 16:00 — 82 commitsWed 17:00 — 39 commitsWed 18:00 — 92 commitsWed 19:00 — 74 commitsWed 20:00 — 169 commitsWed 21:00 — 78 commitsWed 22:00 — 44 commitsWed 23:00 — 44 commitsThu 0:00 — 48 commitsThu 1:00 — 25 commitsThu 2:00 — 48 commitsThu 3:00 — 77 commitsThu 4:00 — 43 commitsThu 5:00 — 9 commitsThu 6:00 — 12 commitsThu 7:00 — 16 commitsThu 8:00 — 9 commitsThu 9:00 — 12 commitsThu 10:00 — 17 commitsThu 11:00 — 42 commitsThu 12:00 — 38 commitsThu 13:00 — 62 commitsThu 14:00 — 146 commitsThu 15:00 — 62 commitsThu 16:00 — 110 commitsThu 17:00 — 60 commitsThu 18:00 — 98 commitsThu 19:00 — 125 commitsThu 20:00 — 66 commitsThu 21:00 — 92 commitsThu 22:00 — 60 commitsThu 23:00 — 38 commitsFri 0:00 — 8 commitsFri 1:00 — 1 commitsFri 2:00 — 5 commitsFri 3:00 — 0 commitsFri 4:00 — 2 commitsFri 5:00 — 0 commitsFri 6:00 — 2 commitsFri 7:00 — 10 commitsFri 8:00 — 12 commitsFri 9:00 — 12 commitsFri 10:00 — 13 commitsFri 11:00 — 24 commitsFri 12:00 — 14 commitsFri 13:00 — 44 commitsFri 14:00 — 66 commitsFri 15:00 — 87 commitsFri 16:00 — 101 commitsFri 17:00 — 122 commitsFri 18:00 — 72 commitsFri 19:00 — 45 commitsFri 20:00 — 100 commitsFri 21:00 — 22 commitsFri 22:00 — 26 commitsFri 23:00 — 13 commitsSat 0:00 — 9 commitsSat 1:00 — 8 commitsSat 2:00 — 5 commitsSat 3:00 — 11 commitsSat 4:00 — 2 commitsSat 5:00 — 0 commitsSat 6:00 — 6 commitsSat 7:00 — 11 commitsSat 8:00 — 3 commitsSat 9:00 — 13 commitsSat 10:00 — 39 commitsSat 11:00 — 62 commitsSat 12:00 — 44 commitsSat 13:00 — 7 commitsSat 14:00 — 78 commitsSat 15:00 — 73 commitsSat 16:00 — 134 commitsSat 17:00 — 74 commitsSat 18:00 — 81 commitsSat 19:00 — 48 commitsSat 20:00 — 133 commitsSat 21:00 — 77 commitsSat 22:00 — 44 commitsSat 23:00 — 30 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Who is committing

last 52 weeks
Maintainer commits5,796 (77%)
Community commits1,702 (23%)

7,498 commits in total over the last year.

DateListRankStars gained
Oct 31, 2026weekly#9+1,854
Oct 30, 2026weekly#9+1,854
Oct 29, 2026weekly#8+1,930
Oct 28, 2026weekly#8+2,296
Oct 27, 2026weekly#3+2,683
Oct 26, 2026weekly#3+2,987
Oct 25, 2026weekly#4+3,241
Oct 24, 2026weekly#3+3,349
Oct 23, 2026weekly#3+3,708
Oct 22, 2026daily#4+684
Oct 22, 2026weekly#3+3,590
Oct 21, 2026daily#4+684
Oct 20, 2026daily#3+564
Oct 19, 2026daily#3+564
Oct 18, 2026daily#8+420
  • morluto/rea

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

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

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

    394.9K stars · TypeScript

  • 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

  • NousResearch/hermes-agent

    The agent that grows with you

    265K stars · Python

  • anomalyco/opencode

    The open source coding agent.

    228.3K stars · TypeScript