Packages

Structured-output enforcer for LLM responses. Repair + validate + (optional) retry-with-LLM. BYO-LLM, BYO-schema.

Universal stream formatter for AI coding agent output

Generated Rust client for the AgentCat API, consumed by agentcat-sdk - placeholder for the generated client, which is in active development.

Analytics for MCP (Model Context Protocol) servers - placeholder for the official AgentCat Rust SDK, which is in active development.

Unprivileged Linux sandbox for AI agents — namespaces, Landlock, seccomp, cgroups

Language-agnostic dependency fingerprint and behavioral regression gate for AI agents

A CLI tool for browser automation via the Chrome DevTools Protocol

A standard way to declare and run agent containers for your projects.

Rust implementation of the AgentContract specification — behavioral contracts for AI agents

Agent Cooperative public package coordinate scaffold

Agent Cooperative public package coordinate scaffold

A minimal Rust crate that gives any application agentic capabilities.

Cryptographic core for AgentCreds - verifiable, attenuable delegation for AI agents, verified offline

Networked DID method resolvers for AgentCreds (did:web, DIF Universal Resolver, did:cheqd / did:indy). Kept out of agentcreds-core so the core has no network dependency and is unconditionally offline; each resolver implements agentcreds_core::did::DidResolver.

Tiny control-plane primitives for AI agents.

Unified auth pool and LLM API client for Claude Max Plan, OpenAI, and more

Deterministic declarative control plane for safe agentic automation

Deterministic domain model, DSL, compiler, policy, and effect contracts for agentctl

Redacted audit and OpenTelemetry-compatible events for agentctl

MCP and A2A clients for agentctl

Native model provider adapters for agentctl

Durable deterministic workflow runtime for agentctl

Versioned SQLite persistence for agentctl

agentctx

Agent daemon for secure capability execution with pluggable isolation backends

agentd — a minimal, MCP-native, reactive agent runtime (the CLI binary over the agentd-core engine)

Minimal, MCP-native agent runtime as a library: the agentic loop, supervisor, workflows, and code-registered tools (the agentd engine)

Reference implementation of the Instruction Specification: parser, validator, delivery pipeline, and signature verification

Model Context Protocol base library: wire types, version/era negotiation, transports

Minimal blocking HTTP/1.1 + SSE over Read+Write, unix/tls/vsock connects, SSRF guard

Interface for agent persistence.

Detect which AI agent harness is running this process (env-var only) + optional OpenTelemetry propagation.

Tower / axum middleware that reads the agentdetect propagation header and emits OpenTelemetry signals.

Reserved crate name for the future agentdev project.

Agent Environment public package coordinate scaffold

Audit and trace autonomous AI code contributions in git repositories

Virtual file tree infrastructure for agent-ready file layouts using CoW reflinks

CLI for agentdir — virtual file tree infrastructure for agent-ready file layouts

Compact agent-facing compatibility facade for DNSpls MCP domain intelligence

Project-scoped AI agent and plugin environment manager

Core library for agentenv - project-scoped AI agent and plugin environment manager

Generate production-ready MCP (Model Context Protocol) servers and clients from OpenAPI specs

Agenterra fork of Rust SDK for Model Context Protocol

Agenterra fork of Rust SDK for Model Context Protocol macros library

Unified agent file installer for Claude Code, OpenCode, Codex, and Cursor

Fit messages to an LLM context window. Token-aware truncation with pluggable tokenizers and multiple strategies.

Optimize AI CLI agents for cost and performance.

AI agent definitions and detection for agentflare

Live shareable artifact pages from AI agent sessions

Caveman markdown compressor — LLM-based prose compression with structural validation