Packages
Browse packages indexed by the registry.
LLM provider trait, streaming primitives, and first-party provider implementations for the Agent SDK
Pure-Rust agent SDK for production tool-calling loops, multi-provider, type-safe, and ergonomic
Filesystem-backed durable store adapters for the Agent SDK.
Scripted Postgres-style durable store adapters for the Agent SDK.
SQLite-backed durable store adapters for the Agent SDK.
Supabase REST-backed durable store adapters for the Agent SDK.
Optional tool-pack helpers layered over agent-sdk-core primitive contracts.
Tool traits, registry, hooks, and store contracts for the Agent SDK
Unified multi-provider search CLI for AI agents — 13 providers, 13 modes, email verification, one binary
App-scoped Wayland capture and input for Linux automation agents
Transport-neutral secret reference contract shared across Agent Infra domains
Ahp public package coordinate scaffold
Portable session IR, parsers, discovery, and process matching for local AI coding-agent transcripts.
Turn native Agent Session logs into auditable cross-runtime JSON facts
Generate and track session IDs for LLM agent conversations
Agent shadowing — monitor, replay, and analyze agent behavior
Toggle shadow mode for agent tool calls: record what would have happened without running real side-effecting code.
Shared parsing substrate for agent hook binaries — JSON input, shell tokenization
Security scanner for AI agent extensions — offline-first, multi-framework, SARIF output
A minimal, stable, easy-to-understand skill installer and manager for AI agents
A package manager for Agent Skills.
Parse, validate, and work with Agent Skills as defined by the Agent Skills specification
CLI for validating and working with Agent Skills
Library and CLI for installing agent skills
Reserved crate for the Matrix Rust SDK
Provider-neutral Agent Runtime source template and repository provisioning contracts
Agent Source Repository local context registry for coding agents
Intent compiler for AI agent coding: human intent compiles through requirement IR into verifiable task contracts, mechanically verified against the code
Provider-neutral Code Graph adapter types, bounded process execution, and conformance gates for agent-spec
Core spreadsheet automation primitives — shared types, edit normalization, and session traits for agent-facing surfaces
Stateful MCP server for spreadsheet analysis and editing — token-efficient tools for LLM agents to read, profile, edit, and recalculate .xlsx workbooks
Bounded native raster renderer for spreadsheet ranges — scene extraction and deterministic PNG rasterization with structured fidelity warnings
A local CLI toolbox for humans and agents.
Generic labeled state machine for AI agent control flows
Tmux-integrated indicator showing which AI coding agent sessions are waiting on user input.
Causal-ordered, backend-pluggable store substrate for the agent fleet — a monotonic generation counter and a per-writer BLAKE3-chained log, with a commit doorbell. SQLite today; Postgres behind a feature gate (Phase 2).
Agent Stream Kit
Curated supplement recommendation engine for longevity biomarker optimization
Machine-first CLI that closes the feedback loop for AI agents authoring SVGs from raster references: render, score (pixel + SSIM), localized diffs, and vision-friendly comparison images.
P2P swarm network for AI agents
Tmux popup TUI for switching between waiting AI coding agent sessions.
Safely synchronize coding-agent sessions and memories over SSH
Canonical configs, fanned out to all your AI coding agents from the Commons, the canonical ~/.agents directory
Lightweight task management CLI for coding agents and humans to collaborate asynchronously
Priority queue of agent tasks with status tracking
CLI for local agent team mail workflows.
Reusable CI monitor core for agent-team-mail
Core library for local agent team mail workflows.
Plugin daemon for agent-team-mail: GitHub issues, CI monitoring, cross-computer bridge