← all releases
InfiniAI Lab·Nov 3, 2026·v0.1.0·open source
Hermit
Hermit is an open-source framework designed for continual learning and recursive self-improvement of AI agents through harness adapter evolution. It allows users to adapt existing agents to new tasks by evolving external adapters without modifying the underlying model or original harness.
Continual LearningAI AgentsRecursive Self-ImprovementMachine Learning Framework
overview
Hermit is an open-source framework designed for continual learning and recursive self-improvement of AI agents through harness adapter evolution. It allows users to adapt existing agents to new tasks by evolving external adapters without modifying the underlying model or original harness.
key features
- 01Trainable harness adapters that do not require modification of the original model or harness
- 02Unified RL-style training loop for evolving adapters based on task feedback
- 03Support for multiple harness evolution methods including GEPA, SkillOpt, and Harness²
- 04Transferable adapter design for reuse across compatible models and harnesses
- 05Native plugin conversion for deployment to various agent hosts
related productsbrowse all →
MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.Letta Code SDKopen sourceThe Letta Code SDK is a software development kit that enables developers to build deeply personalized agents with persistent memory that learn over time. It serves as the interface to Letta Code, facilitating the creation of stateful agents capable of continuous learning and improvement.OB-1open sourceOB-1 is a self-improving coding agent developed by OpenBlock Labs, designed to autonomously handle the full development lifecycle, from project management to pull requests. It integrates seamlessly into existing workflows, enhancing productivity and code quality.