Model Fine-tuning
Training and adapting models on custom data. As of 2026-11-21, 64 indexed products offer it (41 with full profiles), in 6 forms: 25 MCP servers, 24 Agent skills, 9 Infrastructure, 3 Plugins. 8 were published in the last 90 days, against 17 in the 90 days before. distilly has the most GitHub stars, 33% of the total across 36 products with their own repository.
CapabilitySegment label: Lagging the catalogue DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 25 indexed · 4 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | GuaardvarkLocal AI studio on your GPU: images, video, music, voice, RAG. Needs the Guaardvark app installed. | guaardvark | 346 | 1d ago | ||
| 2 | rlhf-feedback-loopRLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO. | IgorGanapolsky | 33 | today | ||
| 3 | CallosiumOne shared memory for every AI you use, in plain Markdown files you own. | callosium | 11 | 2mo ago | ||
| 4 | growmosLiving knowledge graph for your repo: query with citations, remember/link facts, fact-check claims. | codician.com | 9 | 3mo ago |
Agent skills 24 indexed · 23 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | distillyDistilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill). | titanwings | 27k | 1mo ago | ||
| 2 | immortal-skill♾️ 开源数字永生框架 — 从聊天记录蒸馏任何人的七维数字分身。支持微信/飞书/iMessage/Telegram等12+平台,7种角色模板,对齐 OpenClaw Soul Spec 标准。一行指令让你的AI学会蒸馏。 | agenmod | 1.2k | 7mo ago | ||
| 3 | OpenJudgeOpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards | agentscope-ai | 1.1k | today | ||
| 4 | ex-skill致你忘不掉的那个TA,你们干大模型都是码圣 It's giving rebirth era. Welcome to Digital Life 1.0. 🫶 | titanwings | 1.1k | 3mo ago | ||
| 5 | awesome-nuwaAwesome list of 女娲.skill — 用女娲蒸馏的人物思维框架合集 | Distilled human thinking frameworks for Agent Skills | nuwa-skills | 507 | 1mo ago | ||
| 6 | teacher-to-skillsDistill your teacher into a source-backed Skill that teaches you until you can work on your own. | JuneYaooo | 487 | 14d ago | ||
| 7 | arborApplies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI. | K-Dense-AI | — | 5d ago | ||
| 8 | axolotlExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support | Orchestra-Research | — | 1mo ago | ||
| 9 | implementing-llms-litgptImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers. | Orchestra-Research | — | 1mo ago | ||
| 10 | llama-factoryExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support | Orchestra-Research | — | 1mo ago |
Infrastructure 9 indexed · 9 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | SoupFine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. | MakazhanAlpamys | 11k | today | ||
| 2 | oumiEasily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM! | oumi-ai | 9.4k | today | ||
| 3 | second-brain-ai-assistant-courseLearn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques. | itsdecodingai | 3.1k | 7mo ago | ||
| 4 | overmindThe platform for continuously improving AI agents. | overmind-core | 772 | today | ||
| 5 | ai-engineer-notebooksHands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, and customer craft. Runs on the free Groq API. | calmrocks | 756 | 14d ago | ||
| 6 | END-TO-END-GENERATIVE-AI-PROJECTSEnd to End Generative AI Industry Projects on LLM Models with Deployment_Awesome LLM Projects | GURPREETKAURJETHRA | 643 | 1y ago | ||
| 7 | AdaRubricsAdaRubric: Adaptive Dynamic Rubric Evaluator for Agent Trajectories | alphadl | 369 | 2mo ago | ||
| 8 | agentic-rlAgentic RL 中文零基础教程(33 章):从概念到 GRPO 实战,含 TRL 最小可跑示例;26–33 章附一套可运行的三方判别模型实证工程(encoder vs LLM-LoRA vs 规则基线)。第 25 章讲清 Jev / TypeSafe System One 与 RL 的能力边界 | Chinese Agentic RL tutorial (33 chapters) + a reproducible discriminative-model benchmark | cookiespiggy | 150 | 26d ago | ||
| 9 | Rilldex-RL-StudioRL observability for LLM agents: behavior maps, native trainer metrics, rollout investigations, and Python/SQL analysis. | Sheltercosmo | 81 | 14d ago |
Plugins 3 indexed · 2 profiled
2 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | togetherai-skillsAgent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions, image/video generation, fine-tuning, batch inference, evaluations, sandboxes, dedicated endpoints, and GPU clusters. | togethercomputer | 42 | 3d ago | ||
| 2 | datarobot-agent-skillsDataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and external agent monitoring. | datarobot-oss | 34 | 3d ago |
AI APIs 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Together AIInference, fine-tuning and GPU cluster platform for open-weight models with an OpenAI-compatible API. | Together AI | 13 | 1d ago | ||
| 2 | Fireworks AIInference and fine-tuning platform for open-weight models with serverless and dedicated deployments. | Fireworks AI | — | — |
Agent projects 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | awesome-ai-engineering🚀 A curated collection of AI engineering resources, roadmaps, tools, and projects covering LLMs, RAG, AI Agents, MCP, fine-tuning, evaluations, and production AI systems. | dipakkr | 23k | 1mo ago |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 25 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 24 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| OpenClaw | 1 |
| Google AI Studio | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| Telegram | 1 | 1.6% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| fine-tuning | 23 |
| fine tune | 0 |
| lora | 15 |
| model training | 4 |
| rlhf | 7 |
| distillation | 15 |
Segment statistics
Whole catalogue (64 indexed products). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized among capabilities, with launches growing more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.220 means stars are spread as if across about 5 equally popular projects — moderately concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .