Search

AI Agent Execution Debugger - Visualize skill, rule, MCP, agent execution chains across Claude Code, Cursor, and Codex

Open-source memory infrastructure for pi agents - inspired by Honcho. Provides peer representations, reasoning, and context assembly for stateful AI agents.

React SDK for natural language control of web apps via AI agents

AI-powered vibe coder, live debugger, and agent session manager — supports OpenAI, Anthropic, and Google Gemini

TypeScript SDK for in-browser AI agents with UAMP protocol support

Minimal agentic reasoning tool with multiple LLM backend support

AI coding agent with per-tool permissions, cost tracking, and token optimization

The safety net for AI agents. Automatic rollback, approval gates, and intent verification.

Open-source GraphRAG with self-validating trees, agentic retrieval, and pixel-level citations.

Garry's Stack — OpenCode integration + fast headless browser. One repo, one install, entire AI engineering workflow.

An open-source Python toolkit for turning documents, repositories, and web content into a citable, persona-aware assistant

Skill-powered AI agents implementing the Agent Skills specification with pydantic-ai

Praison AI agents for completing complex tasks with Self Reflection Agents

A modern multi-agent AI testing framework

An agentic memory engine designed for lossless, tiered verbatim storage and multi-hop retrieval.

Claude Agent SDK adapter for AgentMark - integrate AgentMark prompts with Claude Agent SDK

AI model: agentlans/flan-t5-small-simplifier

AI model: RichardErkhov/Cadenza-Labs_-_dolphin-llama3-8B-sleeper-agent-distilled-lora-gguf

AI model: sebastian328/llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-400

AI model: sebastian328/llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-1600