A framework for continual learning and recursive self-improvement through harness adapter evolution.
☆536Nov 20, 2026Updated this week
Alternatives and similar repositories for hermit
Users that are interested in hermit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Unified Framework for Efficient RSI Research☆432Updated this week
- ☆17Jun 15, 2026Updated 5 months ago
- RSI-Anything: Unlocking Recursive Self-Improvement with World Models☆1,190Oct 13, 2026Updated last month
- Recurse: a fully local agentic harness built on top of Pi Durable.☆48Updated this week
- A rejection-sampling based distribution alignment method for extreme actor-policy mismatch RL Training☆14Feb 11, 2026Updated 9 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs☆114Jul 26, 2026Updated 3 months ago
- ☆373Updated this week
- ☆17Oct 23, 2026Updated 3 weeks ago
- Repository Markdown, readable system diagrams, and a local Nessa Docs browser.☆135Updated this week
- ☆24,559Nov 2, 2026Updated 2 weeks ago
- Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.☆919Sep 17, 2026Updated 2 months ago
- Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed h…☆2,833Updated this week
- LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flint…☆44Nov 4, 2026Updated 2 weeks ago
- Formal verification workflow and skill stack for coding agents (TLA+, Z3, Apalache, TLAPS)☆87Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆679Aug 21, 2026Updated 2 months ago
- Machine Learning Experiment Tracker and Sweep Manager☆19Updated this week
- SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses☆3,690Updated this week
- A self-evolving agentic OS. A new architecture for agent execution, built on operating-system principles, with the harness as a path towa…☆779Updated this week
- The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu☆3,580Updated this week
- Local MCP messaging between Claude Code and Codex sessions on the same machine☆20Updated this week
- LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization☆61Updated this week
- A toolkit for Weight-Space Programming / Reading☆43Nov 13, 2026Updated last week
- ☆59Nov 13, 2026Updated last week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A training-free multi-agent framework for recursive self-improvement in new environments through broad-then-deep autonomous exploration a…☆618Oct 2, 2026Updated last month
- ☆1,801Sep 23, 2026Updated last month
- HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code…☆4,387Updated this week
- ☆47Updated this week
- Everything you need for building an agent. A Go library for the LLM tool-calling loop with budgets, hooks, skills, and tracing.☆143Nov 3, 2026Updated 2 weeks ago
- An agent paradigm built on an event-driven timeline and a fully plugin-based runtime — it grows and iterates within the environment it r…☆632Updated this week
- Linear Programming for Weight-Space Programming☆51Nov 9, 2026Updated last week
- An AI-built, autonomously evolving harness for local language models. Self-testing, validation, error correction, and continuous improvem…☆14Updated this week
- ☆175Oct 28, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- AgentRun is an open-source platform that supercharges your agents. It adds self-improvement, durable execution and a control plane on top…☆1,233Updated this week
- An open benchmark arena for coding agent harnesses, built for the Pi community☆13Oct 21, 2026Updated last month
- ☆10Nov 6, 2024Updated 2 years ago
- A self-improving RLM agent for coding workflows and long-running autonomous tasks.☆22,860Updated this week
- The workflows and skills the MiniMax Code team uses to build MiniMax Code. Open source, install and use.☆739Nov 11, 2026Updated last week
- A continual learning benchmark built on the three ARC-AGI editions☆38Updated this week
- Disaggregated Prefill-Decode LLM serving engine on mini-sglang with a proved KV page state machine (PdLedger)☆25Nov 11, 2026Updated last week
Are these results useful?