Search

Contract-bounded autonomy for LLM agents: five small primitives that make an agent safe to leave alone.

Official LangChain & CrewAI Tool for Barlas Execution OS.

A terminal-first Python Agent with tools, RAG, validation and session context.

Claude Code 세션 정책 엔진 — 에이전트 폭주(재귀 스폰·예산 소진·반복 루프)를 실행 전에 차단

Role-boundary preservation and identity-drift detection for autonomous LLM agents.

AstriveAI - Universal AI Agent Framework

Agent Arcade — voice-driven control for your AI agents (Electron UI + a shared Go dictation daemon, NDJSON over a local socket).

Engine 7 — Self-hosted AI agent engine

AstriveAI - Universal AI Agent Framework

AstriveAI - Universal AI Agent Framework

CLI client for the Autonomous Agent Execution Engine

agent-tco: Pareto-optimal configuration of agentic workflows.

inis.run sandbox provider for Strands Agents

Turn failed agent traces (wrong tool, bad args, wrong format, over-refusal) into clean tool-call/behavior-fix SFT/DPO training data

Pydantic AI toolset for inis.run sandboxes

Check whether your agent instruction files reach the agent at all: Codex, Claude Code, Cursor, Copilot.

Local developer MCP server with Streamable HTTP, OAuth 2.1, filesystem tools, commands and Git repository context.

22-agent Mixture-of-Agents pipeline with LongLoop for 24h autonomous iteration: smart routing sends easy tasks to Flash, hard tasks to flagships, cutting token costs ~90%. One-command deploy（一键部署，22 个 agent 的 MoA 流水线，长程循环可自主迭代 24 小时，智能路由省约 90% token 成本）

Local-first operating system for AI-agent teams: resource governance, gated workflows, and multi-project orchestration on top of Agent Memory OS.

A local-first agentic coding harness: streaming tool loop, permission gating, context compaction, subagents, and any LLM provider.