Search

A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE. Graph memory, self-learning skills, multi-model routing, sandboxed tools. MCP · ACP · A2A. One Rust binary.

A self-reflection framework for engineering managers

Autonomous AI agent that triages URLs for phishing and malware: a barefoot Anthropic tool-use loop driving 10 classical analysis tools plus a hardened Docker browser sandbox.

jqwiks antidote, keeps your agents safe while using jqwiks by removing poisoned data

AI coding assistant based on Agent Loop architecture with streaming parallel tools, context compression, and semantic memory retrieval

Compiled Go agent reasoning engine — run smart on tiny hardware

🌊 The Semantic Interface Engine for the Agentic Web. Generative UI from JSON specs, with multistep agent action flows.

Production-grade AI agent orchestration — DAG context, self-evaluating pipelines, skill bundles with memory. Inspired by MUSE-AutoSkill, UserHarness ToM, 01 Systems, LeJEPA, Attention Residuals.

A library-science-inspired personal knowledge management system with LLM agents

A working AI agent built in C from scratch — no frameworks, no SDK. ReAct loop, tool system, filesystem sandboxing, 200+ tests.

Android Agent Reliability Runtime A debugging and safety runtime for mobile GUI agents: detect readiness, block unsafe actions, verify progress, diagnose failures, and save reproducible traces.

Framework adapters for the Agent Governance Toolkit (LangChain, CrewAI, OpenAI Agents, and more)

Retrieval access control and vector store policy enforcement for RAG pipelines

Version control for LLM prompts. Zero dependencies, works offline, embeds in any project.

SAULT CLI — agent payments, marketplace services, and curated skills from the terminal

Lemon AI Agent — spawn specialist agents from Node.js APIs with tools, streaming, and structured output

The Veto CLI. Tell an AI agent what to buy. Veto decides if it's safe.

Token-aware rate-limit queue proxy for the Anthropic Claude API. Agents never see a 429.

A Unified Virtual Filesystem For AI Agents

LangChain/LangGraph integration for Credat — authenticate AI agents with trust and delegation