LLMs & Model Tooling
Model-layer infrastructure: training, fine-tuning, prompting and everything that wraps a large language model.
🎯 从零基础到 AI Agent 全栈工程师 · 110 个详细教程 · 58 万字 · 400+ GitHub 项目精选 · Obsidian 友好 · 中文
Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.
Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.
A local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to the model provider. The AI Agent builds its own Harnes.
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.
Open Source Agentic Security Scanner
AI-powered Vibe Investing for NASDAQ, S&P500 & crypto: LLM quant trading tools, multi-agent backtesting, and data-driven market columns (mNAV arbitrage, BTC-Nasdaq coupling, Alpha Arena). 미국 주식·가상화폐 AI 투자 큐레이션·칼럼·트레이딩 봇.
A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.
Linux desktop control over MCP — AT-SPI, GNOME Shell, Wayland portals, ydotool
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.
Last-night exam-cram coach as a Claude Agent Skill: turns your slides, notes and past papers into a chaptered knowledge base + quiz bank, teaches only what's in your materials, and never fabricates (measured 100% out-of-scope abstention). Bilingual EN/中文 — the 期末极速备考 skill.
Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.
LLMInternSkill: LLM internship resume and job-search Codex Skill for resume polish, JD tailoring, evidence guard, interview grilling, and Project Scout. 大模型实习简历与求职工具箱。
Zenith — a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
A curated list of code samples and tutorials for building agents on Gemini Enterprise Agent Platform (previously Vertex AI).
📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | https://misakanet.org
企业级 AI 智能体 Agent 平台，覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测，每个环节都经过深 度设计和工程化打磨。
A library-science-inspired personal knowledge management system with LLM agents
Self-hosted AI agent OS — streaming chat, tool use, persistent memory, and multi-agent teams. Runs entirely on your machine.
Antidote for fluffy specs, a toolkit for fact-driven development with AI agents
Local-first code intelligence for AI assistants. Turns your codebase into a knowledge graph your AI can query, navigate, and remember. 25 MCP tools.
To know what models don't say out loud.
Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.
使用社交软件聊天记录结合向量数据库让AI更好的扮演对方的角色，在不微调模型的情况下可以达到可观的效果。把曾经的美好，续成往后的陪伴。
🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | 生产级外挂记忆系统，兼容Hermes/Claude/Cursor等任意AI智能体
中文优先的 Vibe Coding / AI coding engineering workflow guide: specs, agents, worktrees, skills, CI, and review.
Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.
Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No vector database, just markdown.