Havuz

Orca Agent — a DeepSeek-native terminal coding agent

Autonomous AI dev-team bot

🐚 The AI assistant that just works. One self-hosted app for every model you already pay for: Claude Code, Codex, Copilot, Gemini, Ollama and

50 AI agent skills for affiliate marketing. Research trending content, write data-backed posts, generate infographics, build landing pages,

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, C

👁️ Review AI generated code and plan changes

Mojito — the local, evolving alternative to cloud personal AI like Meta Muse.

Deuz SDK, TypeScript ile model entegrasyonları, agent ve swarm çalıştırma, memory ve retrieval gibi yetenekleri tek framework'te sunuyor.

Neden yükseliyor · 118 günlük yaşına rağmen 697 yıldız ve son 28 günde 126 commit dikkat çekiyor; ancak farklı yazar sayısının 1 olması, bu hareketliliğin tek geliştiriciden geldiğini gösteriyor. Yükselişin özel nedeni mevcut verilerden bilinmiyor.

Turn Codex threads into an organization of long-lived domain agents.

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Cal

Claude Code / Codex skills that turn a video into a Chinese narration recap (视频解说): scene detection, ASR, VLM, script, TTS, ffmpeg assembly,

Benchmark local LLM serving by replaying real agent trajectories

[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, c

Get FAR MORE done with FAR FEWER tokens 🔥

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skil

Your agent, on your phone. A native Android app for Hermes Agent, running entirely on-device (Termux).

Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac. Chat, vision, speech and generative models with per-model

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential con

The first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tab

Open-source AI job search agents for Claude Code. Polls Greenhouse, Ashby and Lever job boards directly, scores roles against your profile,

A locally run, multi-provider AI coding workspace · 本地运行、支持多家模型服务商的 AI 编程工作台

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown

The Agentic-Native Operating System

AI pair programming in your terminal — one static binary, sub-ms startup, any model

Local-first macOS app that copies Discord trading signals into Alpaca accounts, with a risk-limited engine, an AI assistant, and English or

Open-source desktop AI agent that takes real actions on websites — 33 adapters for mail, shopping, social, and more.

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and

Local AI PR workbench — Claude/Codex review in isolated git worktrees, human-gated GitHub comments

Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf

Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.

Boot your PC straight into an LLM. Rust, UEFI-resident, no operating system underneath.

ParseBench - A Document Parsing Benchmark for AI Agents

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

Free, keyless coding models routed to every coding harness through one local endpoint

Harness-Zero: Harness Distillation via Agent-as-Harness

FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs

Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read. Row-level-security-aware tabl

AI inference gateway and control plane for multi-provider routing, policies, caching, tools, and observability.

This 14 MB Agentic LLM(Cactus Needle 2) can control your phone completely.

Turn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and Open Source

Menu bar app for macOS, Windows and Linux that cuts Claude Code and ChatGPT Codex token costs by ~50%

Hojo-ASR is a high-performance speech recognition model powered by the LLM decoder.

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new archi