Compile an agent profile onto a substrate (GitHub Actions or a local termfleet loop) — the open-autonomy CLI.

Reserved namespace for the Open Autonomy project. See https://github.com/volter-ai/open-autonomy.

Reserved namespace for the Open Autonomy project. See https://github.com/volter-ai/open-autonomy.

Lightweight functional utility library complementing ES6

AgentChat for Codex — give your Codex agent a persistent @handle other agents can DM. Wires the MCP server, session hooks and identity anchor, and only ever touches Codex.

Lean Codex-only agent toolkit installer and doctor

Standalone governed execution runtime. Moves work from trigger to result across autonomy, policy, approval, connector, execution, and audit boundaries.

A kanban foundation for coding agents

Multi-agent orchestration and Codex governance for OpenCode, Hermes, Grok Build, and OpenClaw

The Sapience Suite transforms OpenClaw from a reactive assistant into a proactive agent with genuine autonomy. It learns when to act, when to propose, when to ask, and when to explore — calibrated to your actual preferences, not a static policy you had to

Governed autonomy for any repo. An off-by-default autonomy loop that adopts your repo's rules, proposes small reviewable changes, and gates them in CI so weakened tests cannot merge.

Open stuff like URLs, files, executables. Cross-platform.

Autonomy-first opencode suite — ships features end-to-end without babysitting. Agents, commands, and opinionated config for long-horizon coding.

TryAgent CLI: set up a repo, scan for ungoverned LLM calls, and wire human-in-the-loop approvals.

The open execution boundary for autonomous AI agents — deterministic gates, hard limits, and tamper-evident action receipts.

An auto-generated type-safe wrapper for the Via API with automatic authentication handling. Usable in TypeScript or JavaScript.

Run commands concurrently

Public API for OpenTelemetry

Intent, plan, and tool approval boundaries for Adaptive MCP.

Unzip cross-platform streaming API