Havuz

🌃 Capri — Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.

Cost-efficient coding-agent runtime: prefix-aware prompt-cache routing, poisoning-safe semantic cache, budgeted context compression, request

An audit agent that proves whether a person's data is really gone: resolves identity across systems, judges state at the audit cutoff, finds

Next-Gen Multi-Agent Swarm Orchestration Engine. Coordinate 50+ LLM nodes (GPT-6, Claude 5.5, DeepSeek-V4) in a high-speed mesh network. "R

神经元记忆网络 让 DSH 记住「为什么这么决定」，而不只是结论。思维链记忆插件：8 个池分级遗忘、每轮注入、神经元 3D 星云浏览、夜巡自动整理。

50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitti

AI agent with persistent memory, human-in-the-loop workflows, and Telegram integration, built with Make.com, Airtable, and Gemini.

Универсальный Telegram-бот-оркестратор для общения с базами данных (MySQL, PostgreSQL, SQLite) на естественном языке. Использует локальные L

Evidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.

This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind

🔥🔥 Accelerating decision inference with exact state forking

Live trading arena for LLM agents: public reasoning, real market data, virtual capital

Manipulation benchmarks test acting to change; EmbodiedLab tests acting to know. Given only an objective and the apparatus, a robot runs its

Stateful ride-support agent: versioned claims, evidence-backed RAG, durable memory and guarded MCP tools.

Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents

Your own design studio inside the coding agent you already use.

A recursive self-improvement (RSI) workflow that evolves both target agents (e.g., Pi and DeepSeek Harness) and the RSI system itself.

MIT-licensed agent framework for the AxisVela ecosystem: governed agent loop, model/tool/memory/event primitives, plugins, sandboxing, and p

Automate your real iPhone from Safari with a $2 ESP32. No Mac, no APP, and no jailbreak. Local conversations, your choice of AI, and communi

Turn your repos into a team of Claude Code agents with persistent memory, coordinated tasks, and a live dashboard.

Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory

Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.

Instant context compaction for Hermes Agent. Builds the compaction summary in milliseconds with no LLM call, keeping the exact commands, exi

SciPIvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents

Autonomous trading agents with deterministic execution. The agents propose; the system decides.

Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus

An end-to-end framework for Agentic Reinforcement Learning.

Official Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "

An AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark a

Open-source Android assistant that replaces Gemini. Summon it by gesture, bring your own API key, and it reads the screen, taps through apps

Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked

Can coding agents build the agent you actually want? A benchmark of 25 agent software engineering tasks across creation, editing and optimiz

Claude Code skill + 18 AI agents for Android & iOS mobile app security audits. OWASP MASVS/MASTG-aligned, with adversarial exploitation conf

Asamana is an AI-driven emergent narrative engine.

OpenChart, grafikler, uyarılar ve AI agents üzerinden piyasa analizi yapılmasını sağlayan masaüstü trading uygulamasıdır.

Neden yükseliyor · Repo yalnızca 1 günlük ve 46 yıldız almış; bu, ilk ilgiye işaret ediyor ama benimsenme kanıtı sayılmaz. Son 28 günde 23 commit ve 2 farklı yazar var; erken geliştirme hareketliliği mevcut, ancak topluluk ve ürün olgunluğu hakkında güçlü çıkarım yapmak için veri az.

Sno Station Skills: 31 tested skills that turn Claude Code and Codex into one working team. Cross-vendor peer review, automatic handoff when

SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation

Catches multilingual voice agents placing the wrong order. τ-bench style benchmark + CI gate for voice ordering agents in English and Hingli

Official codebase for the paper "Sharpening Tax in Post-Training"

FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads li

Autumn-Recruit Algo Notes(秋招算法学习仓库)，面向大模型时代的算法、工程与AI学习共建仓库。从数学基础、数据结构，到机器学习、深度学习、LLM、Agent、AI-Infra、语音与数据科学，通过「理解→推导→手写 → 运行 → 验证 → 复盘构建可持续迭

按问题复杂度自动分流的电商客服 RAG：简单问题直接回答；复杂问题经过多跳检索并自我纠错；查单、退改通过工具调用完成，且高风险写操作必须先经人工确认。基于 FastAPI 和 LangGraph，混合检索并附带引用，内置离线评测与 Prometheus 指标。涵盖简历写法和项目面

先进且稳定的企业级智能分析平台；面向企业问数、洞察分析的Data Agent，基于数据分析方法论打造可审计、可治理、可复现workflow

Find the best AI models you can run

Cubicle: a live pixel-art office for your AI agents (Paperclip, Claude Code, Codex, Gemini CLI). See who works, who needs you, who failed; K

Asking for What Was Never Requested: horizontal and vertical proactivity in LLM agents. Need-graph metrics (no LLM judge) and Q&D, which tra

Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifac

The control layer for agentic AI. A protocol-aware proxy that applies identity, policy, trust and payment controls to A2A, MCP and DIDComm t

Local-first Agent RL workbench for Search-R1 rollouts, reward evaluation, GRPO/verl training-data handoff, and an auxiliary private RAG work

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.