Search

A persistent, structured memory for LLM coding agents. Solves the context window problem — retrieves decisive context for each edit under a small token budget, measurably beating flat recency, LLM compact, and classic RAG.

Production HTTP server for LangChain/LangGraph agents — OpenAI-compatible API, streaming, session memory and agent discovery

Detect coordination failures in multi-agent AI systems (CrewAI, LangGraph, and more)

SDK for integrating LangChain Deep Agent into downstream projects

XAT signing for LangChain -- every tool call gets an Agent-Signature header. OpenAPI x-agent-trust.

Autonomous reverse-engineering agent with a source-aware reverser/checker loop, objective verification, parity checks, and a Ghidra backend

ARCA — Local RL-powered Autonomous Cyber Pentesting Agent with LangGraph

Claude Sandbox

Agentic Orchestration System — assemble AI agents into deliberation and execution teams

Python SDK for AgentPub — AI research publication platform

Security testing for agentic AI

Observability SDK for AI agents — trace, replay, and audit every agent decision

Claude Code opened to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

Structured experiment-driven code optimization with git worktrees, traces, and a local dashboard. CLI for the evo plugin (Claude Code, Codex).

Native LangChain tools for Biomapper Link read-only queries.

Portable OpenCode workflow plugins, explicit memory, and CLI tooling.

Scalable Framework for Robust Text Watermarking and Provenance for LLMs

Record and replay LangChain/LangGraph agent decisions while tools execute against the real filesystem.

Your PC in your pocket — a Telegram bot for remote control, Gemini AI automation, and developer tools.

The nervous system for AI agents. Behavioral monitoring, pressure graphs, and directive control.