Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
- agents
- calibration
- classification
- decision-making
78,351 visible repositories in the index
577–600 of 763 · Most stars
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
Create characters in Unity with LLMs!
中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调,给出三元组信息抽取微调示例。
All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
A collection of AI Agents papers (Updated biweekly)
GPTeam: An open-source multi-agent simulation
A curation of awesome tools, documents and projects about LLM Security.
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.
A 🇨🇳 and 🇺🇸 translator in your command line
💃 Dance with Intelligence in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
Gp.nvim (GPT prompt) Neovim AI plugin: ChatGPT sessions & Instructable text/code operations & Speech to text [OpenAI, Ollama, Anthropic, ..]
TranslatedDeepSeek Harness self-media workbench plugin: jot down ideas in one sentence, and generate scripts, covers, illustrations, and storyboards with one click
Simple shell script to use OpenAI's ChatGPT and DALL-E from the terminal. No Python or JS required.
Aion 2 AI Prompt Engineering Toolkit - Standalone Desktop Trainer Setup
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
🚀 A real-time monitoring dashboard for Claude Code & Codex, built with SQLite3, Node.js, Express, React, Vite, TailwindCSS, & WebSockets. It tracks sessions, agent activity, tool usage, and subagent orchestration, providing live analytics, a Kanban status board, status notifications, a cute buddy, & an interactive web UI/MacOS/Windows native app.
TranslatedAI Cross-Border E-commerce Operations Agent Toolkit · Breaks operations SOPs down into 7 reusable AI Agent workflows, including prompts, templates, and real-world cases
TranslatedOne-click replacement of the built-in prompts of four AI clients: DSH / WorkBuddy / ZCode / Codex. Double-click to use, self-verifiable, backs up before changes, one-click restore. A single-file exe that needs no Python installation, open source under the MIT license; activation codes are used for server operation and maintenance, and are issued through self-service on the official website.
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
OmniEdu: Open Foundation Models for Learning and Teaching
TranslatedCopy-ready prompts & 54 cases of Opus 5.5 code-rendered videos. Claude Opus 5.5 generates videos with code: cases from across the web and prompts you can copy directly.