Havuz

Serve your models fast on your own infra in 3 steps.

Open-source AI chatbot & site search for your docs. One <script> tag, streaming answers with sources. 100% Cloudflare-native (Workers AI + V

Translate books and documents with LLMs, featuring glossary extraction, review, and polishing pipelines.

BOAR - Adaptive Local Intelligence

Context profiler for LLMs and AI agents - used to introspect context contents and reduce token costs

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

Cut Claude Code costs with sourced levers -- prompt caching, model routing, Batch -- plus an installable skill, CLI tools, a cost calculator

Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right

Spatial prompt engineering through interactive 3D concept graphs

23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex deskto

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

The next easy code and work AI agents harness system: auto, asynchronous, concurrency, efficiently and High accuracy

Local LLM inference engine written from scratch in Rust — hand-written AVX-512 assembly kernels, Metal & Vulkan compute shaders. Supports Qw

Lightweight proxy for LLM

Local CLI and MCP server for compacting test and build output, with retrieval from a redacted local cache.

Open-source desktop AI agent that sees what you see — one hotkey over any window, it answers, acts, or guides you step-by-step.

An AI workforce on your desktop. Describe the work; a team of AI agents does it in the open and hands it back checked. Any model, any harnes

Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.

Canonical eight invariants for AI-assisted engineering: README SSOT, skill guidance, and lightweight checks.

Open, calibrated, single-pass typed-decision models (4B & 27B) for finance and trading

动物塑 AI 的身体参考：内分泌 → 器官 → 耳朵尾巴爪子 → 说话方式。以犬科为例，含亲密场景状态机，附九个真实踩过的坑。

A tool for reading, editing, and writing in Markdown. AI assistant, advanced editor features

Multi-provider AI agent CLI written in Rust

WorkBuddy Multi-Account Manager & Automated Check-in Toolkit (多账号轮换、全域工作区打通与自动化签到)

The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.

面向学生和研究者的 AI 论文教练：自动生成结构化解读、复现 指导、七问回答与可追踪历史记录。

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

领域无关的多 agent UI 自动化测试编排骨架，用 Claude Code 驱动「探索页面→设计用例→写测试→审查」流水线

Curated Claude and Codex skill collection for local AI workflows, automation, research, and product-building.

Open-source bitemporal knowledge graph — long-term memory for AI agents. Hybrid retrieval, conflict-aware ingest, GDPR forget. REST + native

Find and fix web-app vulnerabilities in one command — SAST + DAST + AI, for devs who aren't security experts.

以番号为核心的本地JAV影片库管理工具。自动扫描建库、插件刮削封面与资料、内置 libmpv 播放与本地 AI 日中字幕，兼容 NFO 导入导出。支持 Windows / macOS / Linux，也可用 Docker 部署到 NAS，手机和电视用浏览器即可访问。

为 DeepSeek Harness 打造：选中 AI 回答或思考内容，随时追问、学习、检查与纠偏。

Universal local LLM runtime. Drop-in Ollama replacement with HuggingFace integration, pipelines, structured output. Free & open source.

A tiny, rate-limit-aware OpenAI-compatible proxy for the NVIDIA NIM API, built for agent harnesses like OpenCode, Codex, n8n, and anything e

Papers in, ideas out. Generate research, product, or feature ideas from 250M+ academic papers.

AI code review with DeepSeek: headless PR review automation that verifies PR descriptions claim-by-claim against real code, checks docs agai

Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.

Build AI agents and LLM workflows visually. Security-maintained continuation of Flowise: security fixes, Apache-2.0 only, drop-in for your e

A tiny language model that talks like a house cat named Miso.

Local-first workspace token calculator and model recommender for coding agents, with repo maps, VS Code, CLI, and MCP.

Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilit

Claude skill: turn your current conversation into a complete handoff document so any LLM can pick up exactly where you left off

🐟 闲鱼/Goofish 智能监控控制台：AI 大模型选品 + 收藏降价·售罄即时提醒，全本地运行不外传。Xianyu second-hand deal monitor — LLM-filtered picks, price-drop & sold-out alerts, dea

This repo is a alternative solution for standard self-attention. It uses tree routing with learnable functions for cheaper self-attention wh

Multi-session IDALib MCP router for coding agents. Analyze multiple binaries in parallel with IDA-compatible reverse engineering tools.

Open-source AI that watches and hears your screen and reacts live as any personality you design — for faceless content, autonomous AI stream

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-

Self-hosted, distributed, multi-model LLM inference

On-policy distillation for agents without the environment: replay teacher prefixes instead of live rollouts.