Havuz

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-awa

Open tax skills for AI: 2,250 skills across 266 jurisdictions, every figure cited to the law. Works in ChatGPT, Claude, Cursor and any MCP c

记忆桥 MemoryBridge — 跨设备、跨平台的 AI 共享记忆层 | Cross-device and cross-platform shared memory for AI (CDSMP implementation)

IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experie

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

AutoHarness: Automated Harness Engineering for AI Agents

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

AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

Command Code provider plugin for DeepSeek Harness (dsh). Adds Command Code model access, live model catalog, plan-aware model selection, rea

Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own mo

A free, open-source desktop app for getting work done with AI. It shows you what it would remember before it saves anything.

Your First LLM-Wiki Conversation Knowledge Base

Harness-oriented agent system framework for production-grade LLM agent applications

Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions

AI-native, local-first video editor by Ribbi — runs entirely in the browser. Rust/WASM engine, WebGPU compositing, WebCodecs export; humans

Python package for LLM compression

The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it

A custom Agent OS built to be hackable, heavily inspired by OpenClaw.

Open Source Agentic Security Scanner

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs,

Local editor for importing, managing, running, and injecting APM-backed assistant packages.

破限本地AI女友后宫，Agent+画图语音向量数据库+live2D+桌宠+酒馆角色卡导入+webchat，QQ+Telegram双通道，8G显存可跑 uncensored Fully offline AI girlfriends harem Openclaw/Claude cod

Self-hosted AI roleplay chat platform you run on your PC or personal server, forked from Risuai

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

Draw a store, generate LLM personas, and watch them shop — an isometric 3D sandbox for synthetic-consumer experiments.

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

Servidor MCP fiscal brasileiro: CNPJ, NF-e, NFS-e, CT-e, SPED, eSocial, Simples Nacional, Reforma 2026. 44 tools, zero-cadastro, tabelas off

Open-source AI office assistant for your desktop: describe the result or file you want in one sentence, and Abu plans and does the rest. Loc

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark,

Web UI & dashboard for Hermes Agent — chat, memory, skills, terminal, approvals, multi-agent orchestration. Self-hosted.

distill any book down to its spine

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a

Stop letting your work go unnoticed. Meridian keeps an automatic work journal of what you worked on and what you finished, summarised daily,

LLM inference with 7x longer context. Pure C, zero dependencies. Lossless KV cache compression + single-header library.

Open-source local AI workspace — advancing on-device inference.

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented an

Drive Siemens TIA Portal V20/V21 (STEP 7, WinCC Unified) from any MCP client — create projects, generate PLC & HMI, compile & diagnose. Preb

Zenith: a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orches

Transform any idea into a running AI-powered company

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

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable

A performant markdown library for iOS & macOS that supports streaming

DSH plugin — free OpenCode Zen models for DeepSeek Harness (DSH). Free LLM API, no API key needed. 在 DSH 中使用 OpenCode Zen 免费模型，无需 API key

11 Claude skills for SEO: page audits, linkbuilding, article writing, E-E-A-T audits, semantic gap analysis, link building. Methodology from