33 stories shipped across 3 production repos. 6 coordinated agents. Zero human intervention. Drop into any AI-powered IDE or coding assistant.
Why This Matters
Every AI company is building multi-agent dev tools right now. Antfarm already works.
For AI Companies
Building multi-agent coding tools? Antfarm's battle-tested pipeline handles planning, implementation, testing, and code review autonomously. Integrate it into your IDE, copilot, or agent platform.
For Platform Teams
Your agents write code but who reviews it? Antfarm's 6-agent pipeline includes dedicated verification, testing, and review stages -- catching bugs before they reach production.
For Open Source
Fork the agent-template, define your workflows, run against any codebase. MIT licensed. Works with any LLM backend. No vendor lock-in.
Workflows
Each workflow is a deterministic sequence of agent steps. Same workflow, same order, every time. Not "hopefully the agent remembers to test."
Drop in a feature request. Get back a tested PR. The planner decomposes your task into stories. Each story gets implemented, verified, and tested in isolation. Failures retry automatically.
Point it at a repo. Get back a security fix PR with regression tests. Scans for vulnerabilities, ranks by severity, patches each one, then re-audits after all fixes are applied.
Paste a bug report. Get back a fix with a regression test. Triager reproduces it, investigator finds root cause, fixer patches, verifier confirms. Zero babysitting.
Architecture
YAML + SQLite + cron. No Redis, no Kafka, no container orchestrator. Each agent runs in a fresh session with clean context.
Design Principles
Same workflow, same steps, same order. Every run is reproducible. No hoping the agent remembers to test.
The developer does not mark their own homework. A separate verifier checks every story against acceptance criteria.
Each agent gets a clean session. No context window bloat. No hallucinated state from 50 messages ago.
Failed steps retry automatically. If retries exhaust, it escalates to you. Nothing fails silently.
YAML + SQLite + cron. TypeScript CLI with zero external dependencies. Runs wherever OpenClaw runs.
Memory persists through git history and progress files. The autonomous loop pattern from Ralph, scaled to multi-agent workflows.
Agent Roster
Each agent has its own workspace with identity files: AGENTS.md, SOUL.md, and IDENTITY.md. No ambiguity about who does what.
Decomposes tasks into ordered user stories with verifiable acceptance criteria. Maximum 20 stories per run.
Creates branch, discovers build/test commands, establishes baseline. Prepares the workspace for development.
Implements stories one at a time, writes tests, commits with structured messages. Works in tight loop with Verifier.
Checks each story against acceptance criteria, runs tests, security checks. Approves or sends feedback for retry.
Integration and E2E testing after all stories are implemented. Catches cross-story regressions and edge cases.
Reviews the PR, approves or requests changes with actionable feedback. Final quality gate before merge.
Integration
Antfarm is not a replacement for your agent platform. It is the orchestration layer that makes your agents work as a team.
Antfarm workflows as structured multi-agent sessions. Each agent gets a clean Claude Code context with AGENTS.md instructions.
claude → antfarm pipeline
Antfarm's review pipeline as a Copilot Workspace extension. Agents verify, test, and review Copilot-generated code before it merges.
copilot → antfarm review
Any agent that speaks MCP can join an Antfarm workflow. Define tools, context, and handoff points in YAML.
mcp agent → antfarm orchestration
No platform required. Point Antfarm at any repo and run deterministic agent workflows from your terminal.
antfarm run feature-dev "implement user auth"
Get Started
Requires Node.js 22+ and OpenClaw. No Docker, no queues, no external services.
Install from GitHub
curl -fsSL https://raw.githubusercontent.com/snarktank/antfarm/v0.5.1/scripts/install.sh | bash
or tell your OpenClaw agent:
install github.com/snarktank/antfarm
then run:
antfarm workflow list
Battle-Tested
Not a demo. Not a benchmark. Real production Solana repositories, autonomously planned, implemented, tested, and reviewed. February 2026.
Anchor 0.30 migration, IDL regeneration, TS SDK migration, demo lifecycle. Every commit agent-authored.
Full dependency modernization, Parcel build fix, marketplace demo. From broken to building autonomously.
Rust dependency updates, cargo build-sbf, test restoration, TS SDK. The largest autonomous run -- 13 stories, zero failures.
| Metric | Value | What It Means |
|---|---|---|
| Total Stories | 33 | Autonomously planned, implemented, verified, and reviewed |
| Production Repos | 3 | Real Solana ecosystem projects, not toy examples |
| Regressions | 0 | Verifier + Tester + Reviewer pipeline catches issues before merge |
| Human Intervention | 0 | From task description to tested PR -- fully autonomous |
The orchestration layer for multi-agent software development. Drop-in agent pipelines that turn feature requests into tested PRs. Proven, not theoretical.