Open-Source Intelligent Command Layer

Web Graphical User Interface (GUI) for Gas Town multi-agent orchestrator - A companion interface for steveyegge/gastown

HAMLET is a lightweight, all-in-one framework for building and iterating on LLM agents. It lets you define agents, launch a GUI, instrument runs, and fine-tune models via SFT and RLVR.

Open-source streaming-first Python AI agent framework and console for building, orchestrating, tracing, and operating tool-using LLM agents.

Context governance kernel for LLM agents. Predicts entropy, blocks hallucinations. Pairs with opencode-dcp. llm, llm-agents, opencode, opencode-plugin, context-governance, anti-hallucination, claude-code, cursor, typescript.

A Rust memory system for autonomous AI agents built on three operations from cognitive neuroscience that no existing system implements together: memory compaction, memory evolution, and memory conflict resolution.

A Rust implementation of OpenHTTPA, establishing a novel paradigm for high-assurance confidential computing by enforcing cryptographic termination directly within hardware-isolated environments.

Generic LLM skill and SDLC repo. Primarily aimed at Claude Code but largely useable by any toolset.

Deterministic governance runtime plugin for OpenClaw.

The framework for building AI agents you can actually trust in production.

Lightweight local-first LLM agent infrastructure: SQLite memory, tasks, connectors, and chain automation

给Agent完全自由的环境，让它和人类“平等”——Agent-Human Interface

AI Agent Governance Kernel — trust, approvals, audit

Minimalist Python LLM framework that replaces complex graph abstractions with a clean, stateful interpreter pattern for logic-first AI workflows.

Bunshin is a go port of LangChain / LangGraph / LangSmith — production-grade LLM pipeline primitives with native concurrency, type safety, and single-binary deploys.