Packages

Named counters that reset on epoch boundaries for per-session rate tracking

Composable error recovery strategies for LLM agent tool calls

Tiny in-process pub/sub for agent loop events. Sync-only Rust mirror of the Python agent-event-bus library: register handlers by event name (or `*` for every event), emit, and remove via opaque Subscription handles. Subscriber panics are isolated so the bus keeps dispatching.

Structured event emitter for agent runs. Append-only, JSON-line-serializable events with monotonic ids, run id, and timestamps. Zero deps beyond serde_json.

Structured lifecycle event log for AI agent runs

Non-interactive agent job runner. Runs commands as background jobs and returns structured JSON on stdout.

Feature flags and capability gates for AI agent tool access

agent-fermata

A sandboxed HTTP client for AI agents with SSRF protection, domain policies, rate limiting, and resource controls

Agent File Tools — tree-sitter powered code analysis for AI agents

Generic dot-path accessor for JSON/TOML/YAML configs, usable both as a **Rust library** and as a standalone **`afconfig` CLI binary**. The library is the primary interface: spores embed it to get `get_key`/`set_key` without writing a dispatch table per field. The CLI wraps the same logic for shell scripts and quick one-off edits from any language.

A naming convention that lets AI agents understand your data without being told what it means.

Give your AI agent its own private browser — so it reads the real page, past logins and bot walls, without ever touching yours.

Let your AI agent work your inbox — email pulled into plain files it reads, sorts, and drafts on your machine, with nothing sent until you confirm.

A payment tool for AI agents — send and receive across five networks through one interface, with spending limits you control.

A PostgreSQL interface for AI agents: reliable, structured, explicit, and read-only by default.

Rust slug generation with explicit caller configuration for path and URL path segments.

A UI protocol that lets a tool describe its interface as data instead of code — so a trusted host you own renders the screens and actions, and nothing the tool sends can run on your machine.

Session management, code navigation, and orchestration tools for AI coding agents.

Autonomous OSS-repo health for solo maintainers (Rust port of @p-vbordei/agent-fleet)

Registry of LLM agent tools: callable + schema + side-effects + defaults

A git wrapper that tracks cloned repos and prevents duplicate clones

Public Preview — Rust SDK for the Agent Governance Toolkit (policy, trust, audit, identity)

Public Preview — MCP governance and security primitives for the Agent Governance Toolkit

Agent graph library

Base interfaces for agent-graph checkpoint savers

Conformance test suite for agent-graph checkpointer implementations

Postgres implementation of an agent-graph checkpoint saver

SQLite implementation of an agent-graph checkpoint saver

CLI for interacting with agent-graph

Procedural macros for agent-graph

agent-harmonic-field

Drive LLM coding agents — Claude Code, OpenAI Codex, and local Ollama / OpenAI-compatible models — from Rust behind one trait, with a normalized streaming event vocabulary. Bring your own agent too.

Agent loop harness with local and sandbox tool runtimes, context management, and MCP support

Health status tracker for LLM agent components

Periodic heartbeat recorder and stall detector for AI agents

Homeostatic control for AI agent systems — keeping agents in their operating envelope through feedback loops

Unified hook adapter for AI CLI tools (Claude Code, Cursor, Codex, Windsurf, Kiro, OpenCode, Gemini)

Agent Identity Protocol - cryptographic identity and authentication for AI agents

Core identity primitives for the Agent Identity Protocol

Handshake protocol for the Agent Identity Protocol

Agent identity, key management, and trust verification

Structured image diff with JSON output for agent workflows

Agent inbox protocol abstracts queryable data as email.

MCP server for inspecting Claude Code subagent execution logs

A Rust SDK for building AI agents with multi-provider LLM support

Procedural macros for the agent-io SDK

Claude Code hooks for jj-colocated repos — git guard, workspace creation, and cleanup

WorktreeRemove hook — forgets jj workspaces and cleans up directories

PreToolUse hook — blocks destructive git commands in jj-colocated repos with jj alternatives