AI Tools Radar

AI Tools Radar › Categories › Training & fine-tuning

LLM training & fine-tuning tools

Fine-tuning, LoRA, reinforcement learning, pre-training, distillation and training code or recipes. 11 items in today's radar (data fetched 21 Oct 2026, 14:13 (Berlin time)). Categories are assigned by fixed keyword rules on GitHub topics, repo names, descriptions and Show HN titles; an item can be in several categories. How categories work.

All 393Agents & automation 196Coding assistants & dev tools 168Chat apps & assistants 28LLM inference & serving 36RAG & search 28Training & fine-tuning 11Models & research 36Image, video & audio generation 52Voice & speech 21Computer vision 8MCP, skills & plugins 146Evaluation & observability 22Data & datasets 30Local / on-device AI 45Security & sandboxing 33Learning & resources 48Other 16

Trending on GitHub today (1)

RepositoryStars todayTotal starsLanguageLicenseCreated
1. lyogavin/airllm
AirLLM 2.8T LLM inference with single 4GB GPU
LLM inference & servingTraining & fine-tuningModels & researchLocal / on-device AI
38640,040Jupyter NotebookApache-2.02023-06-12

Trending on GitHub this week (4)

RepositoryStars this weekTotal starsLanguageLicenseCreated
1. lyogavin/airllm
AirLLM 2.8T LLM inference with single 4GB GPU
LLM inference & servingTraining & fine-tuningModels & researchLocal / on-device AI
1,69440,040Jupyter NotebookApache-2.02023-06-12
2. gitleaks/gitleaks
Find secrets with Gitleaks 🔑
LLM inference & servingTraining & fine-tuningSecurity & sandboxing
27830,185GoMIT2018-01-27
3. AI4Finance-Foundation/FinRL
FinRL®: Financial Reinforcement Learning. 🔥
Training & fine-tuning
13716,770Jupyter NotebookMIT2020-07-26
4. NVIDIA-NeMo/Nemotron
Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
Training & fine-tuningData & datasetsLearning & resources
372,190Jupyter NotebookApache-2.02025-10-03

New repos of the last 30 days (3)

RepositoryAgeTotal starsLanguageLicenseCreated
1. Arekejoker/qwen21-nsfw-pose-skill
Qwen-Image 2.1 NSFW/姿势出图 skill：作者级提示词配方 + NSFW LoRA + 136 姿势 VNCCS 人偶控制；适用 Claude Code / Codex / Cursor / OpenClaw
Agents & automationCoding assistants & dev toolsTraining & fine-tuningModels & researchImage, video & audio generationMCP, skills & plugins
8 d3,556PythonApache-2.02026-10-13
2. scaleapi/agentenv-framework
Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.
Agents & automationCoding assistants & dev toolsTraining & fine-tuningMCP, skills & pluginsEvaluation & observabilitySecurity & sandboxing
26 d350PythonApache-2.02026-09-24
3. heaven999b/hello-agent-system
👋 Hello Agent System — learn enterprise AI agent system design by building every production layer from scratch. 17 bilingual lessons (EN/中文) with tested exercises: tools, architectures, reliability, security, evals, distributed execution, cost, RAG, release ops. 企业级 Agent 系统设计训练营
Agents & automationRAG & searchTraining & fine-tuningEvaluation & observabilitySecurity & sandboxingLearning & resources
24 d276PythonMIT2026-09-27

AI launches on Show HN (4)

Show HN postPointsCommentsPosted
1. Show HN: Qwen3-4B with the AI writing tics trained out
HN discussion · by erikkannike
Training & fine-tuningModels & research
1551112026-10-19
2. Show HN: Training a model to identify AI web content from structure alone
HN discussion · by jochenmadler
Training & fine-tuning
74282026-09-22
3. Show HN: TurboGPT: train 22KiB transformer in 13s
HN discussion · by lostmsu
Training & fine-tuning
56102026-09-29
4. Show HN: Building an LLM from Scratch in TypeScript
HN discussion · by baraa_
Training & fine-tuning
3332026-10-14