The agent that grows with you

Maximal token-efficient RAG for headless Claude. Auth-agnostic; slice-level retrieval.

jMRI v1.0 — open specification for token-efficient context retrieval in MCP servers. SDKs, reference server, benchmark.

Local, opt-in control-plane GUI for the jMunch suite (config, index/watcher health, savings/ROI, sessions, agent launch).

Build pipeline for the jCodeMunch Starter Packs: weekly re-index of the pack repos, publishing pre-built SQLite indexes as downloadable pack zips.

The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing

Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ token…

Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ token…

Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed.

Wasteland — federation protocol for Gas Towns

OpenTelemetry observability stack for Gas Town (VictoriaMetrics + VictoriaLogs + Grafana)

A native elisp coding agent running in Emacs

Beads - A memory upgrade for your coding agent

An opinionated list of Python frameworks, libraries, tools, and resources

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

An AI-powered search engine with a generative UI

Search + Chat = SearChat(AI Chat with Search), Support OpenAI/Anthropic/VertexAI/Gemini, DeepResearch, SearXNG, Docker. AI对话式搜索引擎，支持DeepResearch, 支持OpenAI/Anthropic/VertexAI/Gemini接口、聚合搜索引擎SearXNG，…

An autonomous agent that conducts deep research on any data using any LLM providers

MVP for an automated content extraction and RAG system for "The Batch" (DeepLearning.AI). Features dynamic scraping of weekly AI insights, image archival, and a vector-based retrieval pipeline.

This repository contains intelligent browser agents that generate structured AI learning paths using OpenAI's GPT and real-time web scraping from DeepLearning.AI.

A personalized news feed website that aggregates content from AI/ML news sources and Twitter accounts with a clean, modern, dark-themed UI.

The Datris Data Platform - Open Source Version

MCP server for web fetching with Cloudflare bypass, Trafilatura extraction, and smart routing. Free, self-hosted, no API keys.

Native iPhone app for your Hermes agent

A curated list of Model Context Protocol (MCP) servers

Codex Auto Review plugin using hooks

This repository contains the public work I produced, wheter it is research, post, slides, sometimes videos, and materials of my talks.