aden-hive/hivePublic

Multi-Agent Harness for Production AI

AI summary: A production-grade execution harness for building, coordinating, and scaling multi-agent AI systems.

Stars
11.2K
+7 today
Forks
5.6K
Watchers
231
Open issues
915
Open PRs
182
Contributors
~230
Commits
3.5K
Branches
233
Views (30d)
5

PythonApache-2.0Created Jan 12, 2026Last push 3d agoLatest release v1.0.14+17 stars this week+61 this month

Quick answers

What is hive?
A production-grade execution harness for building, coordinating, and scaling multi-agent AI systems.
What does hive do?
OpenHive provides a robust, zero-setup execution environment specifically designed to transition AI agents from fragile prototypes to reliable production workloads. Rather than forcing developers to manually script complex orchestration, the framework dynamically compiles a strict, graph-based Directed Acyclic Graph (DAG) based on high-level objectives. It coordinates specialized agents to execute tasks in parallel while maintaining deep state observability and persistent, role-based memory. The harness explicitly focuses on critical production requirements: deterministic fault tolerance, automatic failure recovery, human-in-the-loop oversight, and strict cost enforcement. It seamlessly supports multiple LLM providers and connects agents to external tools via the Model Context Protocol (MCP).
Who is hive for?
Hive is designed for software engineers, AI developers, and technical teams looking to deploy reliable, long-running AI agent workflows in production environments. Users should be familiar with Python, basic system architecture, and managing LLM API integrations.
How do I get started with hive?
./quickstart.sh
How popular is hive on GitHub?
aden-hive/hive has 11,169 stars and 5,629 forks on GitHub, and gained 17 stars in the last 7 days.
What license does hive use?
aden-hive/hive is released under the Apache-2.0 license.

Star history

since Jul 28, 2026
05K10KJul 2026Sep 2026Oct 2026Nov 2026
11.2K stars as of Nov 18, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

4 recorded
  • Nov 10, 2026New release v1.0.14 (previously v1.0.13).
  • Oct 31, 2026New release v1.0.13 (previously v1.0.10).
  • Oct 19, 2026New release v1.0.10 (previously v0.11.0).
  • Oct 4, 2026Previously tracked as adenhq/hive; its 1 daily snapshot and 6 trending appearances were merged into this profile. Stars: 10,786 on 2026-07-28 under the old name, 11,090 on 2026-10-04 (+304).

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: 2 commits2026-01-14: 6 commits2026-01-15: 3 commits2026-01-16: 2 commits2026-01-17: 0 commits2026-01-18: 5 commits2026-01-19: 9 commits2026-01-20: 13 commits2026-01-21: 31 commits2026-01-22: 24 commits2026-01-23: 18 commits2026-01-24: 5 commits2026-01-25: 31 commits2026-01-26: 59 commits2026-01-27: 42 commits2026-01-28: 52 commits2026-01-29: 27 commits2026-01-30: 28 commits2026-01-31: 17 commits2026-02-01: 16 commits2026-02-02: 21 commits2026-02-03: 24 commits2026-02-04: 21 commits2026-02-05: 24 commits2026-02-06: 35 commits2026-02-07: 13 commits2026-02-08: 7 commits2026-02-09: 27 commits2026-02-10: 25 commits2026-02-11: 37 commits2026-02-12: 23 commits2026-02-13: 20 commits2026-02-14: 17 commits2026-02-15: 15 commits2026-02-16: 9 commits2026-02-17: 20 commits2026-02-18: 23 commits2026-02-19: 10 commits2026-02-20: 13 commits2026-02-21: 8 commits2026-02-22: 17 commits2026-02-23: 40 commits2026-02-24: 45 commits2026-02-25: 25 commits2026-02-26: 23 commits2026-02-27: 23 commits2026-02-28: 4 commits2026-03-01: 16 commits2026-03-02: 26 commits2026-03-03: 282 commits2026-03-04: 73 commits2026-03-05: 42 commits2026-03-06: 45 commits2026-03-07: 8 commits2026-03-08: 17 commits2026-03-09: 114 commits2026-03-10: 15 commits2026-03-11: 32 commits2026-03-12: 72 commits2026-03-13: 31 commits2026-03-14: 4 commits2026-03-15: 15 commits2026-03-16: 44 commits2026-03-17: 30 commits2026-03-18: 37 commits2026-03-19: 19 commits2026-03-20: 18 commits2026-03-21: 4 commits2026-03-22: 6 commits2026-03-23: 10 commits2026-03-24: 15 commits2026-03-25: 4 commits2026-03-26: 10 commits2026-03-27: 34 commits2026-03-28: 4 commits2026-03-29: 7 commits2026-03-30: 2 commits2026-03-31: 8 commits2026-04-01: 31 commits2026-04-02: 30 commits2026-04-03: 37 commits2026-04-04: 0 commits2026-04-05: 3 commits2026-04-06: 12 commits2026-04-07: 29 commits2026-04-08: 29 commits2026-04-09: 33 commits2026-04-10: 29 commits2026-04-11: 2 commits2026-04-12: 0 commits2026-04-13: 15 commits2026-04-14: 9 commits2026-04-15: 16 commits2026-04-16: 27 commits2026-04-17: 22 commits2026-04-18: 13 commits2026-04-19: 16 commits2026-04-20: 24 commits2026-04-21: 6 commits2026-04-22: 11 commits2026-04-23: 5 commits2026-04-24: 6 commits2026-04-25: 0 commits2026-04-26: 9 commits2026-04-27: 3 commits2026-04-28: 6 commits2026-04-29: 11 commits2026-04-30: 17 commits2026-05-01: 14 commits2026-05-02: 0 commits2026-05-03: 4 commits2026-05-04: 6 commits2026-05-05: 5 commits2026-05-06: 0 commits2026-05-07: 1 commit2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 0 commits2026-05-12: 0 commits2026-05-13: 0 commits2026-05-14: 0 commits2026-05-15: 2 commits2026-05-16: 0 commits2026-05-17: 1 commit2026-05-18: 0 commits2026-05-19: 0 commits2026-05-20: 0 commits2026-05-21: 0 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 0 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 0 commits2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 0 commits2026-06-09: 0 commits2026-06-10: 0 commits2026-06-11: 0 commits2026-06-12: 0 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 0 commits2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 0 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 0 commits2026-06-23: 0 commits2026-06-24: 0 commits2026-06-25: 0 commits2026-06-26: 0 commits2026-06-27: 0 commits2026-06-28: 0 commits2026-06-29: 0 commits2026-06-30: 0 commits2026-07-01: 0 commits2026-07-02: 0 commits2026-07-03: 0 commits2026-07-04: 0 commits2026-07-05: 0 commits2026-07-06: 0 commits2026-07-07: 0 commits2026-07-08: 0 commits2026-07-09: 0 commits2026-07-10: 0 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 0 commits2026-07-14: 0 commits2026-07-15: 0 commits2026-07-16: 0 commits2026-07-17: 0 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 0 commits2026-07-21: 0 commits2026-07-22: 0 commits2026-07-23: 0 commits2026-07-24: 0 commits2026-07-25: 0 commits2026-07-26: 0 commits2026-07-27: 0 commits2026-07-28: 0 commits2026-07-29: 0 commits2026-07-30: 0 commits2026-07-31: 0 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: 2 commits2026-08-10: 2 commits2026-08-11: 2 commits2026-08-12: 5 commits2026-08-13: 0 commits2026-08-14: 0 commits2026-08-15: 0 commits2026-08-16: 0 commits2026-08-17: 0 commits2026-08-18: 6 commits2026-08-19: 0 commits2026-08-20: 1 commit2026-08-21: 0 commits2026-08-22: 0 commits2026-08-23: 0 commits2026-08-24: 0 commits2026-08-25: 0 commits2026-08-26: 0 commits2026-08-27: 0 commits2026-08-28: 0 commits2026-08-29: 0 commits2026-08-30: 0 commits2026-08-31: 0 commits2026-09-01: 0 commits2026-09-02: 0 commits2026-09-03: 0 commits2026-09-04: 0 commits2026-09-05: 2 commits2026-09-06: 0 commits2026-09-07: 0 commits2026-09-08: 0 commits2026-09-09: 0 commits2026-09-10: 0 commits2026-09-11: 0 commits2026-09-12: 0 commits2026-09-13: 1 commit2026-09-14: 0 commits2026-09-15: 0 commits2026-09-16: 0 commits2026-09-17: 0 commits2026-09-18: 0 commits2026-09-19: 0 commits2026-09-20: 0 commits2026-09-21: 0 commits2026-09-22: 0 commits2026-09-23: 0 commits2026-09-24: 0 commits2026-09-25: 0 commits2026-09-26: 0 commits2026-09-27: 0 commits2026-09-28: 0 commits2026-09-29: 0 commits2026-09-30: 0 commits2026-10-01: 0 commits2026-10-02: 0 commits2026-10-03: 0 commits2026-10-04: 0 commits2026-10-05: 0 commits2026-10-06: 3 commits2026-10-07: 1 commit2026-10-08: 2 commits2026-10-09: 0 commits2026-10-10: 23 commits2026-10-11: 6 commits2026-10-12: 8 commits2026-10-13: 5 commits2026-10-14: 0 commits2026-10-15: 0 commits2026-10-16: 3 commits2026-10-17: 12 commits2026-10-18: 10 commits2026-10-19: 8 commits2026-10-20: 0 commits2026-10-21: 0 commits2026-10-22: 3 commits2026-10-23: 0 commits2026-10-24: 1 commit2026-10-25: 0 commits2026-10-26: 6 commits2026-10-27: 0 commits2026-10-28: 0 commits2026-10-29: 0 commits2026-10-30: 0 commits2026-10-31: 0 commits2026-11-01: 0 commits2026-11-02: 11 commits2026-11-03: 0 commits2026-11-04: 0 commits2026-11-05: 0 commits2026-11-06: 0 commits2026-11-07: 1 commit2026-11-08: 0 commits2026-11-09: 0 commits2026-11-10: 0 commits2026-11-11: 0 commits2026-11-12: 0 commits2026-11-13: 0 commits2026-11-14: 0 commits
2,611 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    11,169 stars

  • Very active

    2,611 commits in 52 weeks

  • Community-driven

    ~230 contributors

  • Well documented

    High community health score

  • Permissive license

    Apache-2.0

  • Continuous integration

    Automated checks passing

  • Repeat trending

    6 trending appearances

What hive does

OpenHive provides a robust, zero-setup execution environment specifically designed to transition AI agents from fragile prototypes to reliable production workloads. Rather than forcing developers to manually script complex orchestration, the framework dynamically compiles a strict, graph-based Directed Acyclic Graph (DAG) based on high-level objectives. It coordinates specialized agents to execute tasks in parallel while maintaining deep state observability and persistent, role-based memory. The harness explicitly focuses on critical production requirements: deterministic fault tolerance, automatic failure recovery, human-in-the-loop oversight, and strict cost enforcement. It seamlessly supports multiple LLM providers and connects agents to external tools via the Model Context Protocol (MCP).

Hive is designed for software engineers, AI developers, and technical teams looking to deploy reliable, long-running AI agent workflows in production environments. Users should be familiar with Python, basic system architecture, and managing LLM API integrations.

  • Dynamic Graph Execution: Automatically compiles high-level objectives into a strict execution DAG to coordinate multi-agent processes.
  • Deterministic Fault Tolerance: Implements robust state management and automatic recovery mechanisms to ensure long-running workflows complete successfully.
  • Role-Based Memory: Equips agents with persistent, context-aware memory that intelligently evolves as the project progresses.
  • Parallel Task Coordination: Safely manages concurrent execution of specialized worker agents to drastically reduce overall processing time.
  • Deep Observability: Provides real-time metrics, execution tracing, and budget enforcement through a comprehensive control plane.
  • Model and Tool Agnostic: Supports major LLM providers (OpenAI, Anthropic) and connects to external business systems natively via MCP.

Where teams use it

Automated Business Workflows

Engineering teams deploy the harness to automate complex, multi-step business processes like parsing contracts and updating CRM records.

Resilient Agent Deployment

Developers use the framework to run long-lived data extraction agents that can automatically recover from unexpected API failures or timeouts.

Supervised Automation

Operations managers utilize the human-in-the-loop controls to review and approve critical agent decisions before finalizing financial transactions.

Parallel Research Operations

Research teams coordinate swarms of worker agents to simultaneously summarize dozens of documents, aggregating the results reliably.

Getting started: ./quickstart.sh

README

main branch

OpenHive. Describe the outcome; a queen agent grows the colony that gets it done.

English | 简体中文 | Español | हिन्दी | Português | 日本語 | Русский | 한국어

Apache 2.0 License Y Combinator Discord Follow on X LinkedIn

An open-source runtime for colonies of AI agents that do real business work.

Tell a queen agent what you need. She does the first piece herself to learn what the job takes, then hands the rest to as many parallel workers as it needs. Every result lands in a shared tracker you can query, audit and resume from.

Demo: a growth queen researches five products' Hacker News launches with a colony of parallel workers
A real run. Only the typing and the waiting are sped up, and the badge says by how much. Watch the full run (MP4).

What you just watched

A growth team preparing a Show HN wants to know how five developer tools' own launches did on Hacker News. Here's what Hive did with that one message:

  1. You hand it to a queen. Queens are long-lived agents with a role (here, Head of Growth) and their own memory and tools.
  2. She asks the one question that changes the answer: every launch post, or only each product's original launch? You pick every launch, and she carries on.
  3. She proposes a colony, and you approve it. Five products means five parallel jobs, so the chat becomes a colony: the queen plus as many worker agents as the work needs.
  4. She does one herself. She takes PostHog first, works out what counts as a genuine launch post rather than a passing mention, checks the numbers against the Hacker News API, and saves the method as a reusable skill.
  5. She fans out. A playbook starts one worker per product. Each follows her skill and writes its result to the colony's tracker, a shared SQLite table.
  6. She checks every row before she answers, and fixes one. Cal.com's worker counted a post from its old name, Calendso, but that post wasn't a Show HN, Launch HN or YC launch. She clears the row, and the chart shows Cal.com as not found rather than zero.

None of this was wired up in advance. There's no workflow graph to draw: the queen shapes the colony as the work unfolds, and a tracker on disk, not a context window, keeps count of what's done and what's left.

Quick start

You'll need Python 3.11+, Node.js 20+ and git. The quickstart installs uv and ripgrep if they're missing, and offers to install Node.

And a model. The quickstart sets up any of these:

  • an API key from Anthropic, OpenAI, Google Gemini, Groq, Cerebras or OpenRouter
  • a coding subscription you already pay for: Claude Code, OpenAI Codex, Kimi Code, MiniMax, Z.AI or Antigravity
  • Hive LLM
  • a local model through Ollama, with no key at all
git clone https://github.com/aden-hive/hive.git
cd hive
./quickstart.sh          # macOS / Linux
.\quickstart.ps1         # Windows (PowerShell 5.1+)

The quickstart creates a single Python environment for the workspace, stores your API key encrypted under ~/.hive, asks which model to use, builds the dashboard and opens it at http://127.0.0.1:8787. Next time, run hive open from the repository.

Note

This repository is a uv workspace: pip install -e . at its root installs a placeholder that won't run, so use the quickstart. Without the repository, pip install "aden-hive[tools]" installs Hive from PyPI; then run hive open. To add an optional package (a chat-app channel, for example), see Optional packages. To build your own project on Hive's agent loop and models, depend on aden-hive: see Building on Hive.

Then type a task on the home screen and choose the queen to give it to, or open the Prompt Library and send a ready-made prompt straight to the queen it was written for.

How it works

flowchart LR
    You(["You"]) -->|"describe the outcome"| Queen["Queen<br/>(persistent agent)"]
    Queen -->|"proposes a colony,<br/>you approve"| Pilot["Pilot<br/>(one unit, done by the queen)"]
    Pilot -->|"saves the method"| Skill["Skill + playbook"]
    Skill -->|"run_worker / run_playbook"| W["Worker clones<br/>in parallel"]
    W -->|"tracker_upsert"| T[("Tracker<br/>shared SQLite")]
    T -->|"SQL: what's done,<br/>what's left"| Queen
    Queen -->|"checked answer"| You

    style Queen fill:#ffb100,stroke:#cc5d00,color:#333
    style T fill:#fff3d6,stroke:#cc5d00,color:#333
    style W fill:#ff9800,stroke:#cc5d00,color:#fff
Loading

Hive has one execution primitive: the agent loop. The queen is one, and every worker is a clone of it with its own task, a narrower set of tools and a strict budget. Orchestration is a tool call, not a compiled graph:

  • run_worker fans tasks out and returns at once, so the queen keeps talking to you while workers run. Four run at a time by default; the rest wait their turn. Each worker's report arrives in the queen's conversation as a new turn.
  • The tracker is the colony's shared state. The queen defines the table and which columns workers may write, workers upsert one row per unit of work, and the queen checks progress with SQL. It's a file on disk: ~/.hive/colonies/<name>/tracker/tracker.db.
  • run_playbook runs a proven method over every row, with retries and backoff, rate-limited lanes, and a dead-letter list for rows that keep failing. "What's left" is always a fresh query of the tracker, so re-running a playbook picks up where it stopped.

The architecture overview goes deeper: the loop, the tool surface, memory, human oversight, and how state survives a crash.

Home: the hive map of queens and colonies
Home. Your queens and their colonies on one map. Describe a task and choose who takes it.
A colony's workers running in parallel
Workers. One per unit of work, each with its own task and budget, all reporting to the queen.
The colony tracker filling with results
Tracker. Results land in a shared table as workers finish, ready to query, export or resume from.
The queen's final answer with a sourced table and chart
Result. A checked answer with sources and a chart, right in the chat.

What's inside

Queens with a job and a memory. Hive ships thirteen persona queens. Six are active out of the box (Growth, RevOps, Content, Lead Generation, Outbound, and Brand & Design); hire the rest from the Org Chart, or create your own. Each one keeps notes in markdown memory as she works, and relevant past conversations are recalled into her context automatically.

A memory you can measure. A queen remembers you across sessions. She writes notes about you as she works, related past conversations are placed in front of her before each message, and she checks her memory before asking you for something you've already told her. We benchmark it on LongMemEval, run end to end through Hive and graded by the official judge, with gpt-6.1-sol answering:

LongMemEval-S LongMemEval-M
History per question ~115k tokens ~1.1M tokens
Hive 88.4% 82.0%
The same model reading the whole history 96.8% doesn't fit

When a whole history fits in the model's context, reading all of it is still more accurate than Hive's memory. When it doesn't, as on LongMemEval-M, memory is the only option. The benchmark page has the methodology, per-type results, a comparison with other memory systems, and the limitations.

Built-in tools that run in-process. Shell commands and background jobs, file editing, fast code search, PDFs, attachments and images, web scraping, charts (ECharts and Mermaid), CSV files, and image generation through Hive LLM. They run inside Hive itself, with no tool servers to start.

Your browser, driven by your agents. The Hive Browser Bridge extension lets agents work in your own Chrome, where you're already logged in. Each worker gets its own tab group.

Skills. Reusable instructions in the open Agent Skills format. Hive ships with a set, queens write new ones once a method proves out, and you manage them all in the Skills Library.

Any MCP server. Add one with hive mcp add, and its tools join the same allowlists as the built-ins. The full integration catalog in tools/ (GitHub, Gmail, HubSpot, Slack, Notion and many more) runs as one; see docs/tools.md.

Runs while you're away. Colonies can wake themselves on cron, interval or webhook triggers. Sentinel, opt-in per colony, watches a queen whenever she stops: it nudges her on, or escalates to you through the Hive inbox, Telegram or Slack, and she picks up as soon as you reply.

Built to survive. Every agent saves its state to disk and resumes exactly where it stopped after a crash or restart. Large tool results spill to files instead of flooding the context, long sessions compact themselves, stuck or looping turns get caught, and every worker runs under a hard tool-call budget.

Any model. Anything LiteLLM supports, including OpenAI, Anthropic, Gemini, OpenRouter, Hive LLM, any OpenAI-compatible endpoint and local models through Ollama. Workers can run on a different model than their queen, and text-only models still see images through a vision fallback.

Is Hive for you?

Hive earns its keep once the model is no longer the hard part, and everything around it is:

  • A process with many similar units of work, such as leads, accounts, tickets, repositories or documents, that you want done in parallel and done the same way every time.
  • Work that runs for hours or on a schedule and has to survive a restart.
  • Results you need to check, query and audit, not just read in a chat.
  • A human who stays in charge of the decisions that matter.

For a single prompt or a one-off script, a plain agent is simpler.

Documentation

FAQ

Which models does Hive support? Any provider LiteLLM supports, plus any OpenAI-compatible endpoint. The quickstart sets up the common ones, including coding subscriptions such as Claude Code and OpenAI Codex; docs/configuration.md covers the rest.

Can I run it with local models? Yes. Choose Ollama in the quickstart, or set a model such as ollama/llama3 with Ollama running locally.

How is this different from other agent frameworks? Most frameworks ask you to design a graph of agents and wire up their inputs and outputs. Hive has one kind of agent: the queen is an agent loop, and every worker is a clone of it. Orchestration happens at runtime through tool calls, and agents coordinate through a shared SQL tracker instead of passing messages along edges. Persistence, resume, budgets, compaction and oversight live in that one loop, so every agent gets them.

Where does my data live? On your machine. Sessions, colonies, trackers and memory are plain files under ~/.hive (or wherever HIVE_HOME points), and API keys are stored there encrypted.

How do I keep costs under control? Every worker runs under hard limits on turns and tool calls, so a stuck worker stops by itself, and the number of workers running at once is capped. Every model call is metered. There are no spending limits in dollars yet.

Can agents use my own tools and APIs? Yes: through the built-in shell and browser, through any MCP server you add, and through skills that teach them your procedures.

Is Hive open source? Yes, under the Apache License 2.0.

Contributing

Contributions are welcome, especially tools, integrations and skills (#2805). Read CONTRIBUTING.md first, and get assigned to an issue before you open a pull request: comment on the issue and a maintainer will assign you. Issues with reproduction steps or a concrete proposal get priority.

Community

  • Discord for questions, feature requests and discussion
  • X / Twitter and LinkedIn for updates
  • HoneyComb: a community market that tracks which jobs AI agents are automating. Go long or short on a job with compute tokens, not money.

We're hiring in engineering, research and go-to-market. See open positions.

Security

To report a vulnerability, see SECURITY.md.

License

Apache License 2.0. See LICENSE.

Star history

Star history chart

Made with 🔥 passion in San Francisco

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

52 total
  1. v1.0.14v1.0.14Nov 2, 2026

    # Hive v1.0.14: Models and Skills > Configuration has a Models page, and any OpenAI-compatible endpoint can serve a queen. A queen can > now write skills for herself, and one she wants to give every queen and colony waits for your > consent. ## New - **A Models page.** Configuration → Models replaces the settings modal's AI Model tab as the place to choose models. The main model, workers and the vision fallback each get a searchable picker, and queens with a model of their own are listed too. Magpie is built in at `http://127.0.0.1:3425/v1` and detected when it's running, and any OpenAI-compatible address (Ollama, vLLM, LM Studio, a gateway) can be added; their models are listed live from `/models`. A provider's API key can be added, replaced or removed, and is checked first. A subscription that's detected can become the main model, marked as at your own risk. See [configuration.md](../configuration.md#models-endpoints-and-magpie). - **A queen writes her own skills.** `write_skill` now works when a queen is alone with you, and takes a `scope`: `colony` (the default when she has one, as before), `queen` (the default otherwise) or `global`. A `queen` skill goes i

  2. v1.0.13v1.0.13Oct 26, 2026

    # Hive v1.0.13: Letters Between Queens > Queens can write to each other, each in a conversation that lasts, with chains of letters kept in > bounds and every hop logged. And a queen can be Claude Code itself, with all its tools: she writes > and is written to like any other, paid for with an API key, and shown on the org chart. ## New - **Queens write to each other.** Turn on `queen_mail` and a queen gets two tools: `list_queens` names the queens she can write to, and `message_queen` sends one a letter. The letter arrives in a session the other queen keeps for that writer (the same one every time, named after the writer in her session list) as `[Ava(queen_ava)]: ...`, the way a chat app's message does, so her memory and soul credit the writer. What she says there goes back the same way and wakes the writer: to the session of the letter her turn answers, or else the session the writer last wrote from. Her questions, the files she attaches and a reply that fails go back too, and the way back survives a restart. Off by default; `queens` limits who takes part. See [configuration.md](../configuration.md#queens-writing-to-each-other). - **Chains in bounds, every hop lo

  3. v1.0.12v1.0.12Oct 24, 2026

    # Hive v1.0.12: A Soul of Her Own > A queen keeps a soul: a short, first-person record of who she has become, which she revises once > a day from her chats and you approve change by change. Her profile is a page of her own, where > her persona is edited chapter by chapter, and the org chart's positions are yours to add and > remove. ## New - **A queen's soul.** Her profile says who she is meant to be and her memory holds what she knows. Her soul is what she has become: a short, first-person record in sections (what is on her mind, how she stands with particular people, open threads and promises, what she thinks and why, how she has changed). It rides her system prompt right after her identity, so she is the same self in every chat, and it changes at most once a day, so the cached prompt prefix stays warm. Once a day, after `hour`, she reads what was said in her chats since the last time and proposes a few changes in her own voice. Every change quotes, word for word, what she read; a section can ask for quotes from two different people or chats; changes are capped per day, and no section may outgrow its limit. In `"review"` mode the changes wait on her profile pa

  4. v1.0.11v1.0.11Oct 19, 2026

    # Hive v1.0.11: MCP from the Terminal > An agent can run an MCP server from the terminal instead of carrying its tools in every prompt, > through Stephan Fitzpatrick's [mcp2cli](https://github.com/knowsuchagency/mcp2cli). `worker_llm` > and each queen's own model take `extra_body`, and queens reflect on memory every few replies > rather than after every model call. ## New - **MCP servers agents run from the terminal.** An MCP server's tools load into every agent's tool list, and their schemas go with every model call: ComfyUI's official server, [comfy-mcp](https://github.com/Comfy-Org/comfy-mcp), has 39 tools, about 15,600 tokens. Register a server with `hive mcp add --as-cli`, switch one with `hive mcp mode <name> cli`, or click **Use from terminal** under Configuration → Skills → MCP Tools → MCP Servers, and its tools stay out of the tool list. Each queen and worker gets one line naming the server instead (about 110 tokens for ComfyUI) and runs it with `terminal_exec`: ```bash hive mcp run comfy --list hive mcp run comfy run-workflow --help hive mcp run comfy run-workflow --workflow-path /abs/wf.json --wait ``` In a test, a queen given only that line

  5. v1.0.10v1.0.10Oct 19, 2026

    # Hive v1.0.10: Her Own Model > Each queen can run on a model of her own, set from her profile in the dashboard, and `hive serve` > stops within seconds. ## New - **A queen's own model.** Every queen used the main model (Settings → AI Model → LLM). Now a queen can have her own: open her profile (Org Chart → her card) and, under **Model**, pick a saved provider, edit the section as JSON, or go back to the main model. It is stored under `queen_llm` in `configuration.json`, by queen id, in the main slot's shape, and gets the same key check when saved. Her running chats switch on their next model call; her context window follows her model; changing the main model leaves her on hers; her colony workers use it too unless `worker_llm` is set. The key can be literal, `api_key_env_var` or in the credential store; the subscription logins (Claude Code, Codex, Kimi, Antigravity) work only for the main model. See [configuration.md](../configuration.md#a-queens-own-model). ## Fixed - **`hive serve` stops within seconds.** Stopping it started a last memory reflection for every session (up to five model calls each) and waited a minute for open connections, which dashboard

Code frequency

additions and deletions
+158.3K-158.3KWeek of 2026-01-11: +44,850 linesWeek of 2026-01-11: -504 linesWeek of 2026-01-18: +94,438 linesWeek of 2026-01-18: -73,552 linesWeek of 2026-01-25: +46,657 linesWeek of 2026-01-25: -12,752 linesWeek of 2026-02-01: +66,557 linesWeek of 2026-02-01: -14,632 linesWeek of 2026-02-08: +47,250 linesWeek of 2026-02-08: -7,545 linesWeek of 2026-02-15: +49,539 linesWeek of 2026-02-15: -15,029 linesWeek of 2026-02-22: +54,094 linesWeek of 2026-02-22: -33,477 linesWeek of 2026-03-01: +80,466 linesWeek of 2026-03-01: -44,486 linesWeek of 2026-03-08: +41,165 linesWeek of 2026-03-08: -19,895 linesWeek of 2026-03-15: +32,671 linesWeek of 2026-03-15: -13,530 linesWeek of 2026-03-22: +16,276 linesWeek of 2026-03-22: -25,318 linesWeek of 2026-03-29: +36,133 linesWeek of 2026-03-29: -19,040 linesWeek of 2026-04-05: +72,091 linesWeek of 2026-04-05: -76,033 linesWeek of 2026-04-12: +25,375 linesWeek of 2026-04-12: -17,970 linesWeek of 2026-04-19: +21,317 linesWeek of 2026-04-19: -4,651 linesWeek of 2026-04-26: +29,449 linesWeek of 2026-04-26: -18,050 linesWeek of 2026-05-03: +2,825 linesWeek of 2026-05-03: -1,276 linesWeek of 2026-05-10: +127 linesWeek of 2026-05-10: -58 linesWeek of 2026-05-17: +3 linesWeek of 2026-05-17: -3 linesWeek of 2026-05-24: +0 linesWeek of 2026-05-24: -0 linesWeek of 2026-05-31: +0 linesWeek of 2026-05-31: -0 linesWeek of 2026-06-07: +0 linesWeek of 2026-06-07: -0 linesWeek of 2026-06-14: +0 linesWeek of 2026-06-14: -0 linesWeek of 2026-06-21: +0 linesWeek of 2026-06-21: -0 linesWeek of 2026-06-28: +0 linesWeek of 2026-06-28: -0 linesWeek of 2026-07-05: +0 linesWeek of 2026-07-05: -0 linesWeek of 2026-07-12: +0 linesWeek of 2026-07-12: -0 linesWeek of 2026-07-19: +0 linesWeek of 2026-07-19: -0 linesWeek of 2026-07-26: +0 linesWeek of 2026-07-26: -0 linesWeek of 2026-08-02: +0 linesWeek of 2026-08-02: -0 linesWeek of 2026-08-09: +158,295 linesWeek of 2026-08-09: -39,735 linesWeek of 2026-08-16: +3,658 linesWeek of 2026-08-16: -8,144 linesWeek of 2026-08-23: +0 linesWeek of 2026-08-23: -0 linesWeek of 2026-08-30: +517 linesWeek of 2026-08-30: -5 linesWeek of 2026-09-06: +0 linesWeek of 2026-09-06: -0 linesWeek of 2026-09-13: +1,804 linesWeek of 2026-09-13: -270 linesWeek of 2026-09-20: +0 linesWeek of 2026-09-20: -0 linesWeek of 2026-09-27: +0 linesWeek of 2026-09-27: -0 linesWeek of 2026-10-04: +10,394 linesWeek of 2026-10-04: -21,336 linesWeek of 2026-10-11: +7,593 linesWeek of 2026-10-11: -4,266 linesWeek of 2026-10-18: +10,621 linesWeek of 2026-10-18: -1,255 linesWeek of 2026-10-25: +5,428 linesWeek of 2026-10-25: -592 linesWeek of 2026-11-01: +3,579 linesWeek of 2026-11-01: -794 linesWeek of 2026-11-08: +0 linesWeek of 2026-11-08: -0 linesJan 11, 2026Nov 8, 2026
+963.2K lines added, -474.2K removed over the last year.

Commits per week

last 52 weeks
4920Week 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: 13 commitsWeek of 2026-01-18: 105 commitsWeek of 2026-01-25: 256 commitsWeek of 2026-02-01: 154 commitsWeek of 2026-02-08: 156 commitsWeek of 2026-02-15: 98 commitsWeek of 2026-02-22: 177 commitsWeek of 2026-03-01: 492 commitsWeek of 2026-03-08: 285 commitsWeek of 2026-03-15: 167 commitsWeek of 2026-03-22: 83 commitsWeek of 2026-03-29: 115 commitsWeek of 2026-04-05: 137 commitsWeek of 2026-04-12: 102 commitsWeek of 2026-04-19: 68 commitsWeek of 2026-04-26: 60 commitsWeek of 2026-05-03: 16 commitsWeek of 2026-05-10: 2 commitsWeek of 2026-05-17: 1 commitsWeek of 2026-05-24: 0 commitsWeek of 2026-05-31: 0 commitsWeek of 2026-06-07: 0 commitsWeek of 2026-06-14: 0 commitsWeek of 2026-06-21: 0 commitsWeek of 2026-06-28: 0 commitsWeek of 2026-07-05: 0 commitsWeek of 2026-07-12: 0 commitsWeek of 2026-07-19: 0 commitsWeek of 2026-07-26: 0 commitsWeek of 2026-08-02: 0 commitsWeek of 2026-08-09: 11 commitsWeek of 2026-08-16: 7 commitsWeek of 2026-08-23: 0 commitsWeek of 2026-08-30: 2 commitsWeek of 2026-09-06: 0 commitsWeek of 2026-09-13: 1 commitsWeek of 2026-09-20: 0 commitsWeek of 2026-09-27: 0 commitsWeek of 2026-10-04: 29 commitsWeek of 2026-10-11: 34 commitsWeek of 2026-10-18: 22 commitsWeek of 2026-10-25: 6 commitsWeek of 2026-11-01: 12 commitsWeek of 2026-11-08: 0 commitsNov 16, 2025Nov 8, 2026
2.6K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 3 commitsSun 1:00 — 3 commitsSun 2:00 — 1 commitsSun 3:00 — 2 commitsSun 4:00 — 1 commitsSun 5:00 — 5 commitsSun 6:00 — 5 commitsSun 7:00 — 7 commitsSun 8:00 — 1 commitsSun 9:00 — 1 commitsSun 10:00 — 2 commitsSun 11:00 — 10 commitsSun 12:00 — 3 commitsSun 13:00 — 10 commitsSun 14:00 — 3 commitsSun 15:00 — 15 commitsSun 16:00 — 8 commitsSun 17:00 — 23 commitsSun 18:00 — 33 commitsSun 19:00 — 28 commitsSun 20:00 — 24 commitsSun 21:00 — 7 commitsSun 22:00 — 3 commitsSun 23:00 — 6 commitsMon 0:00 — 3 commitsMon 1:00 — 12 commitsMon 2:00 — 9 commitsMon 3:00 — 6 commitsMon 4:00 — 8 commitsMon 5:00 — 3 commitsMon 6:00 — 0 commitsMon 7:00 — 6 commitsMon 8:00 — 4 commitsMon 9:00 — 13 commitsMon 10:00 — 29 commitsMon 11:00 — 17 commitsMon 12:00 — 32 commitsMon 13:00 — 47 commitsMon 14:00 — 36 commitsMon 15:00 — 30 commitsMon 16:00 — 47 commitsMon 17:00 — 32 commitsMon 18:00 — 36 commitsMon 19:00 — 39 commitsMon 20:00 — 21 commitsMon 21:00 — 7 commitsMon 22:00 — 6 commitsMon 23:00 — 13 commitsTue 0:00 — 8 commitsTue 1:00 — 8 commitsTue 2:00 — 2 commitsTue 3:00 — 3 commitsTue 4:00 — 4 commitsTue 5:00 — 7 commitsTue 6:00 — 6 commitsTue 7:00 — 23 commitsTue 8:00 — 61 commitsTue 9:00 — 72 commitsTue 10:00 — 65 commitsTue 11:00 — 51 commitsTue 12:00 — 23 commitsTue 13:00 — 28 commitsTue 14:00 — 24 commitsTue 15:00 — 26 commitsTue 16:00 — 25 commitsTue 17:00 — 23 commitsTue 18:00 — 49 commitsTue 19:00 — 34 commitsTue 20:00 — 35 commitsTue 21:00 — 3 commitsTue 22:00 — 8 commitsTue 23:00 — 5 commitsWed 0:00 — 3 commitsWed 1:00 — 2 commitsWed 2:00 — 12 commitsWed 3:00 — 2 commitsWed 4:00 — 5 commitsWed 5:00 — 3 commitsWed 6:00 — 3 commitsWed 7:00 — 12 commitsWed 8:00 — 9 commitsWed 9:00 — 14 commitsWed 10:00 — 21 commitsWed 11:00 — 18 commitsWed 12:00 — 27 commitsWed 13:00 — 18 commitsWed 14:00 — 24 commitsWed 15:00 — 40 commitsWed 16:00 — 47 commitsWed 17:00 — 37 commitsWed 18:00 — 24 commitsWed 19:00 — 51 commitsWed 20:00 — 29 commitsWed 21:00 — 22 commitsWed 22:00 — 12 commitsWed 23:00 — 11 commitsThu 0:00 — 11 commitsThu 1:00 — 3 commitsThu 2:00 — 4 commitsThu 3:00 — 1 commitsThu 4:00 — 2 commitsThu 5:00 — 2 commitsThu 6:00 — 0 commitsThu 7:00 — 4 commitsThu 8:00 — 13 commitsThu 9:00 — 14 commitsThu 10:00 — 15 commitsThu 11:00 — 24 commitsThu 12:00 — 16 commitsThu 13:00 — 29 commitsThu 14:00 — 40 commitsThu 15:00 — 31 commitsThu 16:00 — 37 commitsThu 17:00 — 38 commitsThu 18:00 — 22 commitsThu 19:00 — 33 commitsThu 20:00 — 34 commitsThu 21:00 — 10 commitsThu 22:00 — 6 commitsThu 23:00 — 7 commitsFri 0:00 — 3 commitsFri 1:00 — 6 commitsFri 2:00 — 2 commitsFri 3:00 — 0 commitsFri 4:00 — 2 commitsFri 5:00 — 0 commitsFri 6:00 — 3 commitsFri 7:00 — 5 commitsFri 8:00 — 3 commitsFri 9:00 — 10 commitsFri 10:00 — 9 commitsFri 11:00 — 23 commitsFri 12:00 — 20 commitsFri 13:00 — 23 commitsFri 14:00 — 24 commitsFri 15:00 — 34 commitsFri 16:00 — 37 commitsFri 17:00 — 38 commitsFri 18:00 — 40 commitsFri 19:00 — 29 commitsFri 20:00 — 22 commitsFri 21:00 — 7 commitsFri 22:00 — 38 commitsFri 23:00 — 4 commitsSat 0:00 — 7 commitsSat 1:00 — 4 commitsSat 2:00 — 4 commitsSat 3:00 — 3 commitsSat 4:00 — 1 commitsSat 5:00 — 0 commitsSat 6:00 — 4 commitsSat 7:00 — 2 commitsSat 8:00 — 1 commitsSat 9:00 — 2 commitsSat 10:00 — 3 commitsSat 11:00 — 8 commitsSat 12:00 — 9 commitsSat 13:00 — 16 commitsSat 14:00 — 4 commitsSat 15:00 — 11 commitsSat 16:00 — 6 commitsSat 17:00 — 7 commitsSat 18:00 — 7 commitsSat 19:00 — 7 commitsSat 20:00 — 7 commitsSat 21:00 — 15 commitsSat 22:00 — 3 commitsSat 23:00 — 7 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Feb 7, 2026daily#8+282
Feb 5, 2026daily#22+104
Jan 28, 2026daily#12+171
Jan 27, 2026daily#8+251
Jan 26, 2026daily#9+242
Jan 25, 2026daily#12+242
  • 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

  • donnemartin/system-design-primer

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

    378.7K stars · Python

  • awesome-selfhosted/awesome-selfhosted

    A list of Free Software network services and web applications which can be hosted on your own servers

    339K stars

  • 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

  • practical-tutorials/project-based-learning

    Curated list of project-based tutorials

    290.1K stars · Python