LLMs & Model Tooling
Model-layer infrastructure: training, fine-tuning, prompting and everything that wraps a large language model.
Agentic runtime in Rust — persistent, supervised agents. Self-hosted, local-first, zero telemetry. Apache 2.0.
Skill to generate the knowledge vault for projects using the Ralph loop
Andrej Karpathy's LLM Wiki pattern as a Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.
Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activation, Hebbian writeback, episodic recall, and post-turn consolidation. Local-first, model-agnostic, AGPL.
Find and govern AI attack surfaces in application code at PR time. Free, OSS, runs offline.
Extends pageIndex into an AI document workspace with multi-format parsing, OCR, visual TOC, custom models, citations, and agentic QA.
Token burn reducer and focus keeper for Claude Code, Codex, Gemini CLI, Cline, Windsurf, Aider, Cursor, Copilot, and more: surgical read hints, PDF/Office/CSV/markdown file interception, 160+ filter & interception rules, compact manifest injection, image shrinking, cache and compact skills, cache MCP calls, and much more.
gap — graph as policy: compile language instructions into typed, verified robot skill graphs and execute them on simulators or real robots
Local-first deep research agent that reads the whole web — even pages behind Cloudflare, Datadome, Turnstile & reCAPTCHA. Stealth fetch + cited reports. MCP-native, MIT.
Drive Claude Code or OpenAI Codex from your phone — resume sessions, stream output, approve tool permissions remotely. End-to-end encrypted, zero-knowledge relay, open source.
Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python, no HTTP microservices, no Docker sidecars.
Money-saving guide to AI coding tools: free tiers, discounts, referral credits & open-source alternatives. 省钱指南。
Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
Tamper-evident runtime records for AI agents. Hash-chained, dependency-free, verifiable by anyone.
Open-source terminal AI coding-agent harness for studying agent loops, tools, MCP, skills, safety, and persistence.
The AI-native JupyterLab — open-source Cursor for notebooks. Cmd+K inline edit, multi-step agent with cell-level tools (read/edit/run), chat with @cell/@file context, ghost-text completion, one-click traceback fix. BYO model: Anthropic, OpenAI, Gemini, Ollama, vLLM. Local-first, privacy-first, fully open source.
A tiny MCP stdio server that exposes DeepSeek as a cheap supervised worker for Claude Code, Codex, or any MCP client.
Apple Silicon mlx with Zero Dependency Java
Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase and Serper, multi-engine search aggregation, structured JSON output, provider fallback, deduplication, and SearXNG alternative architecture for agent workflows.
Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.
A curated collection of 51 production-ready subagents for Gemini CLI. Drop them into .gemini/agents/ and let Gemini delegate the right specialist.
Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.