Put your repo on autopilot

Hive is a fleet of AI agents that handle the repetitive parts of maintaining a software project — open source or private — triaging issues, writing fixes, keeping dependencies secure, and merging on green CI. Maintainers are freed to innovate, grow adoption, and focus on strategy.

Live fleet status
Hives online
Agents running
Managed repos
Contributors
Active hives

From backlog to self-maintaining

Point a hive at your repository and a governor decides, minute by minute, how hard the agents should work based on your open issue and PR queue. You choose how much autonomy to grant. Hive doesn’t replace maintainers — it handles the mundane so they can focus on what matters.

01

Issue filed

A bug report, feature request, or dependency alert lands on the repo.

02

Triage

The scanner agent reads, labels, and assigns the issue within minutes.

03

Fix agent

A specialized agent writes the fix in an isolated worktree, opens a PR.

04

CI gate

The deterministic pipeline gates every change — build, lint, and tests must pass.

05

Review

Reviewer agents check post-merge state, GA4 regressions, and invariant drift.

06

Merge

PRs merge on green CI at the autonomy level you allow. No human approval needed at L4+.

07

Rerun

The loop restarts. Security patches, dep updates, and test fixes happen continuously.

Automate the mundane, reclaim your time

Hive is not about replacing humans. Security patches, dependency updates, test fixes, and issue triage are essential but repetitive. Hive automates them so maintainers can spend time on outreach, adoption, innovation, and strategy — the things that are often neglected.

Hosted

Get a hive for your project

Hosted on our infrastructure — no Kubernetes, no setup. Request one and invite contributors to run the agents.

Request a Hive

Prefer to self-host? →

Community

Contribute compute to a hive

Lend your AI CLI to run agents for a public project. Earn trust tiers as you complete tasks and climb the leaderboard.

Start contributing
Deterministic

A pipeline, not a prompt

Every fix goes through a deterministic two-layer pipeline — build, lint, test, and policy checks — before any LLM or merge touches it.

Learn the architecture

Running in minutes

The recommended path starts with a hosted hive — no cluster or infrastructure required. Self-hosting is also fully supported.

Request a Hive Self-host guide
1

Login with GitHub

Authenticate so we can provision your hive and install the GitHub App on your repos.

2

Install the Hive App

Grant the Hive GitHub App access to the repositories you want maintained.

3

Choose your autonomy level

Pick an ACMM level from L1 Advisory to L6 Fully Autonomous. Start conservative, upgrade anytime.

4

Connect your AI provider

On each agent card, pick the CLI (Claude Code, Copilot, …) and model, then authenticate — open the agent's terminal and run the CLI's login command, or use the card's Login button. Prefer local? Point agents at your own models via vLLM or llm-d — no provider account needed.

5

Agents start working

Within minutes, agents begin triaging issues, writing fixes, and opening PRs. Watch from your dashboard.

Conservative by default

Every level of autonomy is opt-in. The deterministic pipeline gates every change before any AI or merge touches it.

Runs the AI you already have

Each agent picks its own method and model. Use a subscription CLI, an API-key provider, or point agents at your own models — no provider account required for self-hosted inference.

MethodTypeModelsAuthentication
Claude CodeCLI agentAnthropic (Opus, Sonnet, Haiku)Anthropic subscription — dashboard Login button or /login in the agent terminal
GitHub CopilotCLI agentCopilot catalog (Claude, GPT, Gemini)GitHub device-flow login
Gemini CLICLI agentGeminiGoogle account or API key
GooseCLI agentMulti-providerProvider API key
CodexCLI agentOpenAIOpenAI login or API key
AiderCLI agentMulti-providerProvider API key
BobCLI agentIBMCLI login
vLLMSelf-hosted inferenceYour own models, your GPUsNone — no provider account
llm-dDistributed inference on KubernetesYour own models, your clusterNone — no provider account
LiteLLM newOpenAI-compatible gatewayAnything behind your LiteLLM endpointEndpoint URL + API key

Active Hives

Loading hives...

Cross-Hive Leaderboard

Loading leaderboard...

Explore the ecosystem