Packages

Baseten provider adapter for agentkit.

Cerebras Inference API provider adapter for agentkit.

Groq provider adapter for agentkit.

Mistral provider adapter for agentkit.

Ollama provider adapter for agentkit.

OpenAI provider adapter for agentkit.

OpenRouter provider adapter for agentkit.

vLLM provider adapter for agentkit.

Reporting observers and event consumers for agentkit loops.

Task manager abstractions and implementations for tool execution scheduling.

Scripted tool composition backends for agentkit.

Filesystem tools and session-scoped filesystem policies for agentkit.

Shell execution tool and shell-oriented safety hooks for agentkit.

Agent Skills tool for progressive skill discovery and activation in agentkit.

Tool traits, registry, execution, permissions, approvals, and auth for agentkit.

Procedural macro derives for agentkit tools (the #[tool] attribute).

Developer secrets on your phone, provided only to approved commands.

Interface for agent key-value persistence.

Find and scrub secrets from AI coding agent session logs and configs (Claude Code, Codex, Gemini CLI, aider, Cursor and more)

Framework adapter crate for AgentLedger Runtime

Langfuse evidence and trace export adapter package for AgentLedger

MCP adapter crate for AgentLedger Runtime

MySQL adapter crate for AgentLedger Runtime

OTLP adapter crate for AgentLedger Runtime

Postgres adapter crate for AgentLedger Runtime

Runtime reliability layer for Agent Harness stacks

S3-compatible blob store adapter crate for AgentLedger Runtime

Docker sandbox adapter crate for AgentLedger Runtime

CLI tool to prepare codebases for AI agents by generating outlines, memory files, and reading rules

Modular and extensible framework for building sophisticated AI agents in Rust

Core runtime and foundational traits for the AgentLib framework

Observability and logging middleware for the AgentLib framework

Procedural macros for effortless tool and agent definitions in AgentLib

Advanced memory providers and history management for AgentLib

OpenAI model provider integration for the AgentLib framework

Multi-agent orchestration and parallel workflow management for AgentLib

Advanced reasoning strategies (ReAct, CoT, etc.) for the AgentLib framework

Common utilities and event emission systems for the AgentLib framework

One brain for every AI coding agent — shared rules and skills with zero file duplication

AgentLink SDK Core - Platform agnostic core library

Domain model for agentlink: one brain for every AI coding agent

Filesystem adapter for agentlink: symlinks, Windows junctions and privilege probing

AgentLink SDK Native - Native platform implementation using reqwest and rumqttc

AgentLink SDK for Rust - HTTP and MQTT client for AgentLink IM

AgentLink SDK WASM - WebAssembly bindings for browser/Node.js

Linter for AI coding agent harness files (Claude Code, Cursor, Codex, Gemini, OpenCode, Pi)

agentlint validator for Claude Code agent harness files (agents, skills, commands, hooks, settings)

A fast, local-first linter for AI coding-agent configuration

agentlint validator for OpenAI Codex AGENTS.md files

Core primitives for agentlint: Diagnostic, Validator trait, file runner, and output formatters