Runtime per agenti, framework di orchestrazione e applicazioni basate su LLM. Cerchiamo progetti con un modello di esecuzione chiaro, esecuzioni osservabili e una documentazione onesta di ciò che l'agente sa e non sa fare.
497 repository in questa categoria
Ricevi i migliori nuovi repository di questa categoria nella panoramica settimanale.
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
HTMLNessuna licenza rilevataCreato il Aggiornato 5 giorni fa
Public repository for Agent Skills
PythonNessuna licenza rilevataCreato il Aggiornato 2 settimane fa
魔搭紫皮书｜ModelScope Cookbook：面向开发者的开源模型应用实战指南，覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC，从跑通第一个模型到构建实际应用。
Bounded project-memory skills for Codex CLI and Claude Code.
🔥🔥 Awesome Jev: open-source models, projects, benchmarks, and independent evaluations for Jev and System One models.
PythonNessuna licenza rilevataCreato il Aggiornato 5 giorni fa
聊天悬浮窗助手（macOS）：屏幕感知 + 本地小模型判断意图与风险，按话术生成回复候选。纯只读。
Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.
1207 public resources for Jev, TypeSafe AI's System One decision model, indexed by decision pattern. Source citations, dated link checks and scheduled call-site text checks; runtime and performance are not independently tested here. EN/中文, JSON schema and platform compatibility.
PythonNessuna licenza rilevataCreato il Aggiornato 5 giorni fa
Know how much Claude Code, Codex, Cursor, Copilot and 70+ other AI coding tools you have left — a free, open-source macOS monitor on the edge of your screen.
Peer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents.
中文 ｜ English Atria Dawn From Research Questions to Verifiable Results Introduction · Model Downloads · Evaluation · Deployment · License · Contact 🌅 Introduction Atria Dawn is a new-generation agentic model developed by the Shanghai Artificial Intelligence Laboratory.
Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.
A curated list of decision models (System One / typed decision models): hosted APIs, open-weight models, runtimes, SDKs, applications, benchmarks, and papers.
AI System Design - Learn how to design AI systems built on LLMs, RAG, and AI Agents step by step.
Halo is an open-source framework built by White Circle for training large language and multimodal models
PythonNessuna licenza rilevataCreato il Aggiornato 6 giorni fa
JevChat-Windows：聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入，发送永远手动
PythonNessuna licenza rilevataCreato il Aggiornato 4 settimane fa
Spark-x2.5 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models
A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry
Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime
World's first open-source enterprise world model.
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
DeepSeek Harness (DSH) Web 插件聚合生态 · 万物皆插件，通过创意工坊分发｜｜DeepSeek Harness (DSH) Web Plugin Aggregation Ecosystem · Everything is a plugin, distributed via the Creative Workshop
Sketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts.