Havuz

Open-source, local-first AI team workspace. Several AI models work together in one conversation, each with its own provider, model and tool

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

Your own AI workspace on your own machines: chat, agents, coding, knowledge bases (RAG) and fine-tuning with local models. Open source (AGPL

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

Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gatew

Open-source AI agent framework for PHP. Tools, memory, security guards and a ReAct loop built in. Works with Laravel, Symfony, WordPress, Dr

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

A minimal yet ready-to-use AI agent harness, built on best practices for frontier models.

A self-hosted workspace where people and AI agents work together

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. F

Claude and ChatGPT now log into your app as your customers. OneHuman decides what they can see and do. Join our community: https://discord.g

Evidence-backed attack paths, drift, and cost auditing for Hetzner Cloud.

The complete cookbook for Jev by TypeSafe AI — 120+ use cases, 10 runnable examples, 4 composition patterns, and first-principles theory for

Myrtia — agent-native red teaming for LLMs and AI agents: a deliberating council of attacker models (propose, cross-critique, Borda vote, ch

Jev-Mem: System-One Controlled Agentic Memory

Lightweight, async multi-agent framework with native SQLite persistence and handoffs for WhatsApp, Telegram, Webhooks, and CLI. Production-h

Desktop terminal for running Claude Code, Codex and Antigravity side by side, with one Inbox for when they need you.

DSoR (Data System of Record): the governed layer between AI agents and a company's real systems. It checks permissions, limits and approvals

An open database of real-world AI agent incidents.

DrugTargetWorld: a synthetic biobank for training and benchmarking AI scientists on end-to-end drug target discovery. Paper: arXiv:2610.0955

Agent skills for designing, training, evaluating and improving application-specific decision systems. Primitive/model selection, data assemb

Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, rout

An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

Self-hosted AI coding agent platform for GitLab, built with LangGraph. Reviews merge requests, resolves issues autonomously, and chats with

Typed, confidence-aware agent skill routing with TypeSafe Jev.

The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into

Give your coding agent a delivery process you can trust. Spec → Plan → Build → Acceptance → Ship.

EvoOntology, data agent’ların farklı veri kaynaklarındaki kavramları ve ilişkileri kullanabilmesi için MCP üzerinden erişilen, etkileşimlerden güncellenebilen bir ontology layer sunuyor.

Neden yükseliyor · Agent’ların kurumsal veriyi anlamlandırma sorununa, MCP entegrasyonunu ve kendini güncelleyen ontology yaklaşımını bir arada sunma iddiasıyla dikkat çekiyor. 13 günde 427 yıldız, 22 commit ve 3 farklı yazar erken ilgi ve geliştirme hareketliliği gösteriyor; bu veriler tek başına kullanım veya etkililik kanıtı değil.

AgentScope Java, Java ile uzun süre çalışan ve dağıtık ortamlara taşınabilen agent uygulamaları geliştirmek için bir framework sunuyor.

Neden yükseliyor · 13 günlük yaşına rağmen 108 yıldıza ve son 28 günde 12 commite ulaşmış; Java tarafında üretim odaklı agent altyapısı arayanların ilgisini çekmiş olabilir. Ancak yıldız ve README özellikleri benimseme ya da üretim başarısının kanıtı değil; farklı yazar sayısının 1 olması katkı tabanının şimdilik dar olduğunu gösteriyor.

Local-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or local and API models (Ollam

Online explainability for LangGraph agents through counterfactual planning and reasoning provenance graphs.

Live Benchmark for long Horizon tool using Agentic Systems

A local agent workstation: one Go loop, three doors: Wails desktop, browser, and CLI. It writes code, reviews hunks, opens an isolated brows

RAM efficient terminal agent harness for coding, cybersecurity, and automation.

Your job landing in one conversation

Human in the loop for agent workflows

Autonomous agent that mines Java deserialization gadget chains from any JAR directory. Static bytecode analysis + dynamic JVM probes + dual-

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

Run coding agents autonomously with isolated Git worktrees, independent verification, and human-controlled integration.

A IDA CLI tool built on Rust, idalib-rs, and idalib. Supports batch and concurrent IDA analysis processes, design for stateless, agent first

Redpen makes coding agents prove they are actually done.

Open-source Windows AI IDE built with .NET 10 WPF, featuring a fine-tuned local AI router (1.5B), live Blender & Unity copilots, self-healin

The agent that evolves with you 𖤍

Agents Universe, ekiplerin ortak proje bağlamı ve yetkilerle çalışan AI agent’ları kurup koordine edebildiği, self-host edilebilir bir platformdur.

Neden yükseliyor · 17 günlük bir repoda 325 yıldız ve son 28 günde 130 commit dikkat çekiyor; bu, kısa sürede ilgi ve yoğun geliştirme olduğunu gösteriyor. Ancak katkı iki farklı yazarla sınırlı ve bu veriler tek başına gerçek kullanımın ya da ürün iddialarının doğrulandığını göstermiyor.

Open-source AI agents for coding, research and automation. Run locally with your models, persistent memory, multi-agent execution, skills,

Guia extenso sobre o Maestri: +257 templates de partitura em 12 áreas, documentação, dicas e recursos para reger times de agentes de IA. Par

MCP-native multi-agent architecture with desktop agents and human-in-the-loop gates

Dissenyador visual de workflows i graphs d’IA agentiva · Diseñador visual de workflows y graphs de IA agéntica · Visual designer for agentic

Research Software Engineering skills for AI coding agents