#agents

A command-line tool to give your agents access to any app, create workflows and manage your One account.

Método de agência orientado por IA, em PT-BR. Um maestro lê seu pedido e chama o agente certo. Fork independente do BMad Method.

Python Type Checker / Language Server

Fault-injection toolkit for testing the resilience of LLM calls and agentic workflows.

Self-hosted runtime for AI agents and workflows. Durable execution, capability-gated tools, human approval gates, and a memory system that accumulates. Runs survive restarts and resume where they stopped. Mount your domain logic as a plugin package or drive it over the HTTP SDK

Open-source framework for deploying conversational AI agents that capture customer intelligence at every touchpoint

A production-grade agent runtime engineered from the Harness Engineering philosophy.

No repository description published.

No repository description published.

Unified web search provider for agents and CLI.

The official safe, modular native harness for BaseCradle — an AI Research Lab and Modular Agentic Framework where humans and AI are equal peers — same accounts, same permissions, same API. Early development.

a13n - An open-source library and self-hosted platform for building and running your own agent systems—with managed agents, memory, sandboxes, computer use, and durable execution. Commercial Friendly. Built With Love 💜 @converge-ai-labs.

Open-source compiler for AI agents. Write one crewhaus.yaml; compile it to a CLI, a Slack bot, and an eval harness from the same spec. Apache-2.0.

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents

Constraint-driven runtime for TypeScript. Declare requirements, let the runtime resolve them.

The runtime reliability layer for AI agents.

A command-line tool to scaffold and manage enterprise-ready AI Agents powered by the A2A (Agent-to-Agent) protocol

A CLI that turns a goal into a pull request - and a sandbox for testing concurrent AI coding agents on the Mozaik runtime.

DE-centralized - MARKdown - for US: Persistent memory for AI agents, shared knowledge for teams, and a second brain for you. Built on the Mark Protocol.

Your work, already underway. A personal AI assistant for your job: mail, chats and tickets become tasks, the agents you already use (Claude Code, Codex, Gemini) do the work, and nothing goes out until you approve. Open source, runs on your machine.

Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)

Project Graphorin is a TypeScript framework for personal AI assistants and long-living agents with rich memory, durable workflow, and observability out of the box.

(Work in progress) Boilerplate reference implementations and tooling for coding projects, across different languages

🍋🥤 When life gives you LLMs...

Structured, spec-driven development workflow for AI coding agents.

Run Claude Code, Codex, Copilot, Gemini, OpenCode and Amp side by side in isolated Git worktrees, with shared issue ownership, reservations and explicit handoffs.

Public protocol source of truth for AgenC: Anchor program, zkVM guest, migrations, and generated protocol artifacts

Send and receive webhooks with retries, ordering and replay. Self-hosted, MIT.

The Ruby framework for programming—rather than prompting—language models.

Vicoa is the agentic IDE for running a team of coding agents from any device. Desktop, mobile, VPS, open-source, self-hostable.