Showing 30 of 5,146 · Category: LLM
Local-only QQ group chat digester: decrypt your own nt_msg.db, build a rolling index, generate reports, and recognize key images. 本地解密 QQ 聊天库并总结群聊，不登录、不注入、不上传。
Open-source AI stock picker for Claude Code: 10 Claude agents scan every US stock weekly, pick up to 5, and grade themselves against a random control. 189 broker-verified trades published. Not investment advice.
postbuch.net – selbst gehostete Dokumentenverwaltung mit KI
OAuth to OpenAI-compatible API reverse router & proxy for Omnirush.ai with Multi-Account Pooling and Cloudflare Worker support
HackYeah 2026 finalists and uploads, scored out of 100 by an AI council against each task's criteria
Pick Your AI: a PCPartPicker-inspired builder for complete AI stacks. Explore components, compatibility, and costs in a preview using synthetic data.
AIE640 – Artificial Intelligence Applications | Hacettepe University, Institute of Informatics | Assoc. Prof. Dr. Hakan Emekci. Hands-on graduate course on Large Language Models (LLMs): transformers, prompt engineering, RAG, fine-tuning & multimodal AI.
A free, open-source AI infrastructure roadmap: a 9-layer map of the stack, 6 stages with exit criteria, around 200 vetted open-source projects, and the math behind them.
How we cut our AWS Bedrock bill by 93%- replacing OpenSearch Serverless with Aurora x pgvector ($700/mo → $50/mo)
The official CLI for Mixlayer. Run open models like DeepSeek, Qwen and GLM from your terminal and your coding agent.
A plan → execute → judge loop for Claude Code: an operator plans each unit, a fenced executor does it, the judge checks against git, with a live work log and a spirit you can talk to.
AI 大模型面试手册：Transformer/RLHF/RAG/微调/推理/Agent/Prompt 等 100+ 问（基础/进阶/实战分级）
Free, open-source expense tracker that fills itself in from your bank SMS and email. Runs entirely on your phone, encrypted, with optional on-device or bring-your-own-key AI. No account, no server, no ads.
Your repository’s tutor, for you and your coding agent. Local, grounded in the code, on your own subscription.
Acceptance testing for LLM systems via role subagents (Claude Code plugin) · Приёмочное тестирование LLM-систем ролевыми субагентами
Self-improving multi-agent harness for Claude Code. A Technical Lead plans, Full-stack builds, QA verifies, and retros turn lessons into rules that fit your project. Stack-agnostic.
Lets your Hermes agent answer with Telegram stickers: default packs out of the box or packs you choose, picked by emoji or by meaning, sent as a reply in the right topic, paced like a person.
Long-term conversational memory and a context compiler for multi-agent character chat. Runs offline; plug in any OpenAI-compatible model.
Biblioteca de documentação que oferece contexto a LLMs de maneira que consiga criar, de forma autonoma, componentes e circuitos via edição de arquivos do software Hades Simulation Framework.
Find the hole in your bug bounty report before the triager does. Pre-submission review for bounty reports and smart-contract findings, on your own model key.
Local agent development workspace with coordinators, terminals, task automation, and annotation feedback
Token optimizer for AI coding agents - Claude Code, Codex, Cursor, Aider, Gemini CLI, Cline, Windsurf, Copilot.
The Universal AI Development Operating System (AI-OS) for Cursor, Claude Code, Antigravity & Copilot. Stop AI amnesia and context drift with an in-repo framework featuring quota-safe handover, 4 golden disciplines, PreToolUse guard hooks, and slash commands.
Self-hosted AI tutor (bring your own API key) that turns your books, online documentation, and YouTube videos into a course. It maps the concepts, tests what you know, and teaches the rest with references to the sources.
AI Dungeon Master for D&D 5e (Claude / Codex) · Настольная ролевая игра с ИИ-мастером
Academic writing rules for Claude, distilled from real paper-editing sessions, open to contributions
Your AI coding agents as one team on your own computer: Claude Code, Codex, Cursor, OpenCode, Copilot, Muse Code, Kilo and more, on the models you pick. Free, MIT, Windows/Mac/Linux.
Replace repetitive LLM calls with small, auditable ML models. Record → Shadow → Live, LLM kept as fallback.