AI Agent Assembly is an open-source governance platform for AI agents. It enforces policy, tracks budget, and audits every action your agents take across three independent interception layers — in-process SDKs, a sidecar proxy, and eBPF kernel hooks — so you can ship multi-agent fleets without losing control of what they do.
| Repo | Purpose | Version | Base branch health | Activity |
|---|---|---|---|---|
 |
Core Rust monorepo: gateway, policy engine, CLI, API, dashboard |   |
 |
   |
 |
Python SDK (PyO3 native + pure-Python client) |   |
 |
   |
 |
TypeScript SDK (napi-rs native + JS client) |   |
 |
   |
 |
Go SDK |   |
 |
   |
 |
Organization profile, templates, support, and community files | — |  |
  |
 |
Homebrew tap for aasm |
  |
 |
  |
 |
Public documentation site |  |
 |
   |
 |
Shared specifications and protocol contracts |  |
 |
  |
 |
Runnable sample code for every SDK plus policy, approval, audit, trace, and runtime workflows |  |
  |
Sample code starts here: agent-assembly-examples is the canonical entrypoint for learning by running small, framework-specific examples for Python, Node.js/TypeScript, Go, policy enforcement, approvals, audit, trace, and runtime workflows.
brew install ai-agent-assembly/homebrew-agent-assembly/aasm# pip
pip install agent-assembly
# uv
uv add agent-assembly
# poetry
poetry add agent-assembly# pnpm (recommended)
pnpm add @agent-assembly/sdk
# npm
npm install @agent-assembly/sdk
# yarn
yarn add @agent-assembly/sdkgo get github.com/ai-agent-assembly/go-sdkA published container image is coming soon. No image is available on
ghcr.ioyet.
curl -sSf https://raw.githubusercontent.com/ai-agent-assembly/agent-assembly/master/scripts/install-cli.sh | shA short hosted alias (
https://install.ai-agent-assembly.dev) is planned but not yet live — use theraw.githubusercontent.comURL above for now.
agent-assemblyis on a pre-stable beta channel — see the Core release badge above for the current version.- The Homebrew tap's
Formula/aasm.rbnow ships real, publishedsha256checksums for the releasedaasmartifacts — the earlier zero-checksum bootstrap state is obsolete.
- Lowest-intrusion integration: one-line init across major agent frameworks.
- Three-layer interception: semantic to protocol to kernel, with selectable depth.
- Secret Injection: real credentials never appear in LLM context windows.
- Tool Execution Sandbox: isolated execution to reduce security risk.
- Human-in-the-loop Gate: high-risk actions require human review.
- Agent Identity and Zero-trust A2A
- Cost and Token Budget Governance
- Org / Team / Agent hierarchy management
- Audit Trail and Compliance Export
- Local Dev Mode (zero-config, OSS)
- SaaS Cloud (managed enterprise control plane)
Prioritize these three above the fold: lowest-intrusion integration, Secret Injection, and Human-in-the-loop Gate.
Start at the org profile, then follow these for every production repository:
| Resource | Link |
|---|---|
| 📚 Documentation site (canonical) | https://ai-agent-assembly.github.io/agent-assembly-docs/ |
| 🤝 Contributing | CONTRIBUTING.md |
| 🔒 Security policy | SECURITY.md — report privately to security@agent-assembly.dev |
| 💬 Support and questions | GitHub Discussions |
Each repository README links back to this profile and out to the canonical documentation site, so you can navigate from the org entrypoint to core runtime, SDKs, Homebrew tap, docs, and spec — and from any repo back here.