OpenClaw-RL: Train any agent simply by talking
- async
- memory-systems
- open-claw
- openclaw-skills
142,187 visible repositories in the index
1–19 of 19 · Most stars
OpenClaw-RL: Train any agent simply by talking
AI Powered Knowledge Graph Generator
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
不在身边的时候,TA 还在这里。Upload real chat logs, rebuild a digital persona — open-source AI companion with persona distillation, an emotion engine, 11 LLM providers, and a graduation mechanism.
Reinforcement Learning via Self-Distillation (SDPO)
An Open Source Toolkit For LLM Distillation
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
Official implementation for "Towards a Unified Self-Distillation Framework for Large Language Models" (https://arxiv.org/abs/2605.06597).
Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline
Awesome List for On-Policy Distillation
An open-source platform for long-duration multi-agent workflows. This project automates long-running, multi-agent AI work by distilling each agent’s output into context for the team of agents. You can let the distilled context to drive each agent.I hope this project can save people's time and be cost effcient- since Deepseek models are cheaper.
Get FAR MORE done with FAR FEWER tokens 🔥
EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.
Prompt engineering for developers
Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.
A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedicated skills/<name>/ directory — a project skill that becomes the single source of truth every AI agent (Cursor, Claude Code, Codex, Windsurf, Gemini) consults before every task.
AI Code Security Anti-Patterns distilled from 150+ sources to help LLMs generate safer code.
From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.