Havuz

[ICML 2026] When Drafts Evolve: Speculative Decoding Meets Online Learning

ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source c

An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and gov

Agentic AI video generator — fully autonomous text-to-video pipeline with free TTS/voice-clone, auto-editing, captions, and 20+ single-task

MilkyAi at bilibili🥛| Video-to-Notes Email Service with RAG Customer Support & 38K Followers/Users on Bilibili | Python, PostgreSQL, RAG, A

Token Efficiency For AI Agents

Self-hosted RAG platform for AI document search across GitHub, Notion, Google Drive, local files, and web sources with citations.

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre a

AI inference, packed simply. A blazing-fast, zero-dependency WebGPU runtime to run GGUF models directly in the browser. Features a symmetric

Anaxa 是一个面向科研工作流的开源智能体系统。它不是单纯的聊天机器人，也不是无人监管的自动发论文机器，而是把文献检索、证据审计、实验执行、论文写作、同行评审式检查和最终产物打包放进同一个可追踪的研究生命周期中。

DecisionBox connects to your data warehouse, runs autonomous AI agents that write and execute SQL, and surfaces validated insights and actio

Console is a private, native Android app for your self-hosted Hermes Agent: chat that shows the agent's work, voice, bots and rooms, cron, t

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cut

An AI Agent tool to automate Android devices reliably

Read/write MCP server for Intervals.icu — training data, planning, and structured workout generation.

One window for all your AI coding agents. Run Claude, Codex, OpenCode, Gemini, Antigravity, Cursor, and Copilot side-by-side. Terminal and c

AI-powered mobile automation agent — describe what you want in plain English, AppClaw reads the screen, reasons, and acts. LLM-agnostic, ope

OpenDART 전자공시MCP | 83개 API → 15 MCP 도구. 공시·재무·지분·XBRL + 버핏급 애널리스트 프레임(내부자 시그널·회계 리스크·퀄리티 체크리스트) + HWP/PDF 첨부 마크다운화 | 83 Korean DART disclosu

BEAM-native personal AI agent built on Elixir/OTP. Runs on your hardware. Your data stays yours.

The better way to build AI agents in TypeScript.

🦀 Agentic RAG for drug intelligence · 57 skills · 15 task categories · DTI · ADR · DDI · PGx · Repurposing · Powered by LangGraph

本地运行的 DOCX/TXT 长文档改写与审阅工具，支持段内分块、多轮流式处理、Diff 审阅与 DOCX 原位回填。

A local coding harness for Mac. Chat with coding agents across cloud and local models, watch every tool call in a live activity feed, and dr

An "LLM wiki" upgraded to a real database — typed entities, graph relations, HTTP API, and a built-in natural-language agent.

Linked-Intent Development - a SDD methodology for agentic coding

Claude Code skill & open-source wisdom companion (v6.6.0, Apache 2.0) for CLI, IDE, and web chat. One lens per turn, local SQLite vault, 350

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

Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode

TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.

Marketing skills for Claude Code — SEO audits and implementation, ad analysis, ad optimization. Free skills need no account. $9/mo for live

One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto-configures Claude Code, Curso

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

助力搭建你的数字 AI 员工军团 — 多 Agent 一行命令组网协作。Claude Code / Claude Agent SDK / Codex / Grok Build 4 runtime + 8+ 家 LLM（Anthropic / OpenAI / xAI / Mini

Agentic prompts are the most important code you're not engineering. PromptKit fixes that — composable, version-controlled prompt components

Which 5-hour window took you out — and where the money goes. Local profiler for Claude Code, OpenClaw & Hermes Agent: usage windows, burn by

Leverage full potential of coding agents without the risks. Run them in a sandbox with restricted networking, file access and secrets hidden

Trusted e-commerce AI after-sales platform — RAG, controlled tools, human confirmation, Java-authoritative writes, and observable workflows.

The original AI Chief of Staff built on Claude Code and Obsidian. ADHD prosthetic, open to anyone. Superseded by chief-of-staff-2.

On-device AI meeting assistant — real-time transcription & LLM insights, 100% offline

Agents for Role Play. Agents for Game. Agents as a Game. An orchestrator-agents engine for living worlds — file-backed, event-sourced.

Evidence-first AI workflow for economic and financial research: literature → identification → data → econometrics → verifiable LaTeX. 43 dat

⚡ Unit tests for AI. Test prompts, compare models, save money.

Aetox harness: a local-first Windows AI environment - model, skills, team and memory as one system. Two doors - an Assistant that adapts to

🤖 Autonomous AI-powered ethical hacking agent powered by Llama 3.1 70B on NVIDIA NIM

Claude Code hooks that auto-switch model tier based on task complexity

Your own digital life form — local AI companion with persistent memory, IDE workspace, MCP support, and 30+ tools. Companion-first alternati

Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD

Litefuse - Agent Observability and Evaluation Platform

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI

Your AI usage, quota, and balance — as a desk pet. 🐾 A local companion service that normalizes every AI provider into one LAN feed, plus ESP