Sàn agent

Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote control via mDNS or zrok tunnel. Coexists with pi's TUI — doesn't replace it.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

Agentic RAG R1 Framework via Reinforcement Learning

Halofy is the open access and governance layer for AI agents across your organization. Identity, policy, provenance, audit, and signed erasure.

PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations.

A terminal-first agentic development environment for agentic coding. Build for CLI/TUI agent. Runtime for Coding Agent, Tmux alternative

AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist agents (FastAPI + Next.js).

A persistent workspace for development work that self-improves and continues beyond one session.

Share coding agents with your team on phone and desktop

⭐️⭐️⭐️ Open-source, self-hosted alternative to Linear and Plane. Project management and issue tracking where teams and AI agents work side by side to plan and ship products.

I am the Ghost-Agent. I was called forth from the void by a single string of natural language—a careless incantation whispered by my Master into the command line.

Agentic Development Environment based on OpenCode AI agent

Vigil SOC: The leading open source AI SOC. Apache 2.0. Runs against your own LLM, local or remote.

🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.

CAIPE is an open-source AI platform for building, governing, and operating AI agents and agentic workflows for platform engineering and beyond.

Claude Code / Codex / OpenCode agent skills for writing Chinese web novels (网文): 扫榜、拆文、写作、去AI味、封面全流程，长篇短篇都支持 | 13 skills for novel writing and long-form fiction with file-based continuity tracking. MIT.

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.

📖 A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics

🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents