The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
Repository Index
89,572 visible repositories in the index
1–15 of 15 · Most stars
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
A persistent workspace for development work that self-improves and continues beyond one session.
- agent
- agentic-ai
- agents
- kiro
PhyAgentOS is a Recursive Self-Improving (RSI) physical agent operating system that enables agents to recursively self-improve through agentic workflows.
- embodied-agent
- embodied-ai
- agent
- harness
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
- proof-assistant
- lean4
- ai-agents
- ai-for-math
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
- agent-skills
- agentic-ai
- cli-tool
- domain-adaptation
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.
- agent
- large-language-models
- llm
- post-training
Latest Advances on System-2 Reasoning
- benchmark
- macro-action
- mcts
- o1
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
- evolutionary-algorithms
- rsi-ai
- self-improvement
- llm-agent
A framework for continual learning and recursive self-improvement through harness adapter evolution.
A lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.
- ai-agents
- benchmarking
- llm-evaluation
- python
A Unified Framework for Efficient RSI Research
- agent
- recursive-self-improvement
Self-improving code for any git repo: give it a measurable goal, a coding agent (Claude Code or Aider) proposes changes, the kernel scores them, keeps winners and rolls back failures. Open-source AlphaEvolve / FunSearch-style evolution loop, sandboxed, with an auditable ledger.
- agent-harness
- ai-agents
- aider
- alphaevolve
HarnessMM: recursive self-improvement for harness token efficiency
- agent-harness
- llm-agents
- recursive-self-improvement
- token-efficiency
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
- agent-framework
- agentic-workflow
- aiforscience
- llm-agents