Explore live open-source projects and AI models.

Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.

Outline-Driven Development for Codex CLI - methodology + skills + agents for OpenAI Codex coding workflows.

🧠 Session memory lifecycle plugin for Claude Code — structured markdown memory, workstreams, handoff, auto-save hooks

Proof-of-concept implementation of the Agentic Context Engineering (ACE) framework — demonstrating Generator-Reflector-Curator interactions for self-improving LLMs on the HotpotQA dataset.

A Ghidra MCP Server for Claude Code - Binary Analysis Made Adorable. Keywords: ghidra, mcp, ghidra-mcp, model-context-protocol, binary-analysis, reverse-engineering, decompiler

adaptive database query systems that fix their own mistakes and optimize performance automatically using Stanford's Agentic Context Engineering

Web2LLM.txt – A fast, open-source website-to-LLM context file generator. Paste any https:// URL and instantly get a clean llm.txt file with token & cost estimation—ideal for RAG, prompt engineering, and AI training workflows.

Applied reasoning, persistent agent memory, context engineering, and human-governed trust for AI coding agents — Claude Code, Claude Cowork, Codex, Cursor, Antigravity. Compatible with Obsidian.

Opensource AI development agent suite for solo founders. Deploy 11 specialized agents in Claude Code with one command. https://buymeacoffee.com/jamiewatters

Evaluate and optimize your AI agent context. Save tokens, save money.