Havuz

Personal-Model First Self Evolving AI Agent 🐘

Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activa

Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs

멀티에이전트 Claude Code 하네스를 위한 토큰 비용 lint — 10 카테고리 × 31 sub-patterns 분류학 + 정적 감사 스크립트 + LLM 0회 결정 트리. Korean primary, English mirror.

Agentic coding in the terminal: the model writes its own multi-agent workflows (Gigacode). Provider-agnostic, local-first, 15+ model provide

An agentic law firm. Yours. 67 specialist AI agents that review documents through evidence-backed debate, with mandatory human gates and a 1

Turn Claude Code into an equity-research agent: 24 analysis skills (Anthropic's open-source bundle + community), a single data MCP, and a pe

面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成，支持 A 股研究｜Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM tr

Cognitive training practices for AI agents. Self-applied. Open source. Built by an independent Vancouver yoga studio.

企業 GenAI 轉型成熟度診斷與導入方法論工具包 — L1-L5 成熟度模型 + 八階段顧問結構。Enterprise GenAI transformation maturity assessment & implementation methodology toolkit (

The AI-native JupyterLab — open-source Cursor for notebooks. Cmd+K inline edit, multi-step agent with cell-level tools (read/edit/run), chat

zerostack, Rust ile yazılmış; birden fazla LLM sağlayıcısını ve kodlama iş akışlarını destekleyen hafif bir coding agent’tır.

Neden yükseliyor · 138 günlük yaşına kıyasla 1692 yıldız ve son 28 günde 75 commit ile dikkat çekiyor; Rust tabanlı hafiflik iddiası ve geniş özellik kümesi ilgiyi açıklayabilir. Yıldız artışının zaman içindeki hızı elimizdeki ölçümlerden doğrulanamıyor.

An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, a

An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of

Turn a goal into a supervised run.

Curated archive of agentic AI samples, reference implementations, and tooling from the Agentic AI Acceleration program in Korea. AWS-native

Companion repo for Agentic Graph RAG (O'Reilly, Anthony Alcaraz & Sam Julien) — 50 runnable skills + 8 pedagogical notebooks covering all ei

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drif

Open-source desktop AI agent: built-in free model, local GGUF models via llama.cpp, dispatch tasks from WeChat/Feishu/DingTalk. Files, brows

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

Desktop IDE for working with multiple AI coding agents. Supports Claude, Codex, OpenCode, Cursor and Grok.

Exploring agent "thinking" animation.

Codebase for Hidden in memory: Sleeper memory poisoning in LLM agents

Production-Grade AI Agent Development Full-Chain Guide: Development, Testing, and Base Framework

ESP32 Wi‑Fi CSI radar for human presence & movement detection. Privacy‑first — no cameras, no sensors, just Wi-Fi signal jitter. Real‑time W

Multi-agent exploratory data analysis system with autonomous insights, visualization, preprocessing, and reporting workflows.

Model Context Protocol (MCP) server for KiCad, enabling Agentic AI workflows for SCH and PCB design.

Open-source coding agents memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that al

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

Open-source, self-hostable alternative to ChatGPT and NotebookLM — agents, skills, MCP, and cited knowledge in one AI workstation. Your mode

Rove — the agent multiplexer for your terminal. Run coding agents on parallel tasks with isolated worktrees and persistent sessions.

CubeLoop — a Pythonic, async-native agent harness core designed for high performance, readability, and production-grade persistence.

Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.

A browser for LLMs, not humans.

backlog: Your AI agent forgets between sessions. Backlog remembers.

Agentic Voice Notes for iPhone and macOS - Rust, Dioxus, LanceDB + RIG + SQLite

A standalone terminal agent in a single C file. Model agnostic (14 providers + local hako), skill-driven, tool permission gated. No node, no

本地优先的 AI 投资研究工作台（AI investment research workbench），支持深度调研、证据化投资论点、投资组合风险分析、自选股与 Pi Agent 副驾驶。

Stop re-explaining yourself

Self-hosted AI workspace built around context management. Works solo, scales to teams.

Gatemole compiles human-owned intent into obligations, links evidence artifacts to those obligations, and produces deterministic release dec

Open-source control plane for AI agents on your own Kubernetes infrastructure, with per-agent costs, access controls, and audit logs.

A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional

专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。

Runtime economic governance for AI agents. Circuit Breaker adds risk-managed execution, cost ceilings, and kill switches to autonomous AI wo

MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in dynamic and adaptive

Local-first, IM-native AI coworker runtime with async role agents, trace replay, evidence, and agentic evaluation.

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release