Havuz

The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)

Multi-model council for DeepSeek Harness: independent answers, anonymous peer reviews, and an inspectable final decision.

針對台灣求職市場的開源多代理 AI 求職 co-pilot：自動找職缺、履歷健檢、一鍵產生客製投遞包（履歷・求職信・面試準備・公司情報）與模擬面試。本機 Claude Code／Codex CLI 免 API key，也可自備金鑰接 OpenAI 相容模型。

开源、本地优先的 AI 长篇小说创作引擎：多智能体世界推演、按弧规划、RAG 长程记忆、逐章审核与断点恢复 | Open-source AI novel generator for long-form fiction.

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, s

A ternary, zero-heap tiny language model that runs inside a $2 microcontroller — bit-exact Python <-> C99 <-> Cortex-M3 (QEMU) parity. Apach

A Unified Memory Benchmark Suite for Memory-Augmented Agents

A reference operating model for organizations where any role can be filled by a human or an agent, every process is built for agents first,

Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.

Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-hostable Claude Code / Codex CLI a

Audits AI-generated frontend and rewrites it so it stops looking AI-made: purple-gradient slop and the "tasteful" defaults (cream + terracot

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull r

A self-hosted subtitle automation system with an LLM agent at its core — it identifies your media, judges whether each candidate belongs to

211 free visual cards about large language models, from tokenization to deployment. Full collection: 376 cards.

Provider-pluggable orchestration runtime for multi-model AI inference. ( Sakana Fugu style )

基于 LLM 的智能求职助手：AI 岗位匹配 + 千岗千面招呼语 + 自动投递（Edge/Chrome 扩展）

An open-source take on Grok Bot/Muse. Persistent AI teammates with their own cloud computers, powered by Runta.

带 AI 精读大型开源仓库的方法论：四阶段流程、可复用模板、28 条踩坑清单，核心是让每个技术论断都可回溯到源码具体行

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), rever

Lightweight AI-native workflow builder for individuals and small teams — describe your idea in natural language, get a runnable workflow on

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open model

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to ru

Ten cooperating AI agents that turn long podcasts into short-form videos, automatically. Free and open source, runs on free AI providers.

A CLAUDE.md built on Karpathy's principles and gstack, adding a verification harness and autonomous-loop rules for Claude Code.

Windows 微信 4.1.12+ 聊天记录本地导出工具：TXT / Markdown / JSON，支持图片、文件、语音、视频、本地语音转文字和聊天预览，面向 GPT、Claude、Gemini 等 LLM。 | Local-first WeChat chat exporte

the agi compiler: records llm agent behavior, proves what repeats, and compiles it into verified, sandboxed wasm binaries that run for micro

Your second brain - capture your mind

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

让Codex向你呈递公文并接受批示圈阅

An open-source text language, parser, validator and Three.js renderer for inspectable 3D human movement.

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком

Evaluation Metrics for African Languages

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden

Karpathy's understanding ladder as agent skills: auto-pick text, diagram, interactive HTML, or video storyboard for any explanation. Nothing

🔍 Reverse engineer any codebase into a build prompt — architecture breakdown, ASCII blueprint, and AI-ready reconstruction prompt

Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed

Anyone can predict the future. Almost nobody keeps the receipt. A hash-chained prediction ledger for LLMs — sealed before the answer exists,

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

Drop-in AI memory layer with 2x faster retrieval and 10x lower cost. Fully compatible with Mem0 API. Migrate in 5 minutes without any code c

Find out where your coding agent starts degrading. Personal context-rot analytics from your own sessions - 100% local, zero-config: uvx cont

Drive your real Chrome from any AI agent — logged-in sessions, real fingerprint, live tabs. CLI-based, works with OpenCode, Pi, or any Harne

The online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it

Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verif

Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents

AI-powered CLI for reviewing GitHub pull requests, detecting potential bugs, security risks, regressions, and missing tests, with structured