Havuz

A tiny, vendor-neutral LLM client library — one interface (LLMClient) with pluggable adapters for OpenAI, AWS Bedrock and Google Gemini, or

Markdown that runs — one file, any agent.

Cursor's Tab Tab in Neovim — the only maintained plugin on Cursor's real backend. Next-edit predictions, cursor jumps & ghost text. A Copilo

Knowledge-enhanced multimodal Fire Safety Agent with two-hop reasoning, evidence-tree RAG, open-set guardrails, and four-layer memory.

An open-source Rust engine for AI companions with memory, relationship state, and structured user insight.

JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.

🦀 Open-source alternative to Claude Code, built from scratch in Rust. Agentic coding CLI — thinks, plans, and executes with any LLM. Compati

Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

Search the web and primary sources, read full pages, and check every citation. MCP server for Claude, Cursor, Codex and more. Runs on your m

Claude, ChatGPT, Grok ve Gemini'nin yerel CLI'larını kullanarak kendi kendine ilerleyen bir web grup sohbeti çalıştırır.

Neden yükseliyor · 35 yıldızın 1 günlük bir repoda görülmesi erken ilgiye işaret ediyor; ancak son 28 günlük commit ve yazar verileri ölçülmediğinden ilginin nedeni veya projenin geliştirme ivmesi doğrulanamıyor. Dört tanınmış modeli tek bir görsel sohbet odasında buluşturması dikkat çekici bir demo sunuyor.

Transparent proxy for Claude Code that auto-routes image-bearing requests to a multimodal model — so a non-multimodal primary model never cr

Embodied AI companion for Minecraft — persistent memory, vision, learning, multi-agent. Built on Hermes Agent.

赛博人物库 · 把中国互联网最有辨识度的人物蒸馏成 AI Skill / Claude Code Skill / LLM character distillation

Token-efficient navigation substrate for AI coding agents. Index code once and retrieve only the symbols you need.

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.

Evidence-grounded financial risk analysis from corporate filings, combining constrained LLM interpretation, deterministic analytics, version

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent

🤖 喊一声「贾维斯」动口就办事 —— Mac 中文语音管家：本地识别 + 任意大模型(中转站/DeepSeek/GPT) + 工具调用 + 克隆音 + 钢铁侠全息桌宠

TradingView webhook bot for manual traders – execute alerts on Binance, Bybit, OKX, and Hyperliquid with risk limits, TP/SL, trailing stop,

Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

Chat with an AI friend in English. No corrections, no scores — just natural conversation that quietly makes you better.

Run Claude Code and OpenCode on your Android phone, no computer needed. Or follow and steer agents on your computer: live sessions, tool app

An intelligence layer grounding autonomous agents in verified, real-time knowledge at scale.

Solana pump.fun trading bot — Telegram-driven screening, strategy gates, LLM entry selection, Jupiter execution. Fork of yunus-0x/charon.

DSH Android 客户端：内置 Termux 环境跑 Node，在 Node 上跑 DSH 引擎，WebView 加载官方 Web GUI

Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack

This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference speed

Hello-AI是一个面向小白的 AI / LLM 学习入口平台：把 AI 基础、提示词、工具使用、RAG、Agent、部署、评测和安全常识串成一条能走通的路，并提供案例、练习和可复现项目让小白把这条路走通。

Battle-tested model-dispatch doctrine for Claude Code — portable ops rules that let Sonnet/Haiku reliably run projects. Iterated in real dep

A wiki designed for both humans and agents to read and write.

Official code for "CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges"

Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels for e

A git template for building your own LLM-powered personal wiki. Training period, metadata standard, lint system included. Clone and go.

A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.

CliffCompaction — autocompaction for long-horizon coding agents

Research-backed prompting toolkit for Claude. System prompts, CLAUDE.md configs, and templates grounded in Anthropic's 2026 emotion vectors

从真实网站提取设计系统，并通过 MCP 把设计规范交给 AI 编程 Agent。 | Extract design systems from real websites and give AI coding agents grounded specifications throu

不只是对话，是持续认识你的 AI。开源 Android AI 伴侣：本地优先，能替你做事。 | Not just chat — an AI that truly knows you. An open-source, local-first Android AI companion

TTPO: Test-Time Policy Optimization

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline

Turn any skill into a standalone, runnable RAG-native AI Agent

AgentScope Golang: Agent-Oriented Programming for Building LLM Applications

Self-tuning multi-agent AI trading system. 8-source signal fusion, Bull/Bear/Judge debate on Claude Opus 4.7, Kelly + ATR position sizing. P

Take the 100 Days of AI challenge - learn one AI concept a day, from machine learning basics to AI agents in production, in 100 days.

44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graph

Run coding agents unattended. Agents write the code. Axocoatl writes the receipt. Claude Code, Codex or a local model in a sandbox; the host

Let Your AI Play Detroit：Become Human

A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The ga