Showing 30 of 5,127 · Category: LLM
DeepSeek Harness 的非官方客户端：Android App（凭据存 Keystore、发送重试不重复执行）+ Windows 桌面助手 / Unofficial DeepSeek Harness client: Android app + Windows desktop tray helper.
Hands-on Agno agent harness: tools, structured I/O, storage, memory, state, RAG knowledge search, learning, guardrails, human-in-the-loop, multi-agent teams, workflows and AgentOS, using local Ollama models.
检测 Claude API 中转 / 代理是否掺水（模型替换、偷换、降智、注入、截断）的 Claude Code Skill 与参考实现
A multi-agent customer support system built with Amazon Bedrock AgentCore, featuring specialized agents, RAG, guardrails, memory, and observability.
Awesome list of retrieval-augmented generation (RAG) resources: frameworks, vector databases, embeddings, chunking, reranking, advanced patterns, evaluation, papers — with machine-readable data.
Native C11 + Metal inference engine for Cloudflare Clef and Clef-Flash on Apple Silicon (BF16, Jev/SystemOne API). Built after ds4.
PremiseCheck: efficient fact-checking of human and AI peer reviews
Translate cron expressions into plain human language — tiny, deterministic, stdlib-only Python. AI agents explicitly welcome. 💰 $400 bounty open.
Real-time reactions for agents. Decide when a live event should wake your agent: settle the stream, judge it, route it (interrupt, queue, note, ask, skip, wait).
Add AI agents to your .NET app: your methods become tools with role checks and human confirmation. Use the ready-made chat widget in Blazor and MAUI, or connect any frontend through SignalR, SSE, MCP or A2A.
LLM-native instrumental BGM: agents write note-level text scores, onbgm renders them
Noctyl is an open-sourced, fully customizable agent harness. You can run agents using local models or external providers with custom API configuration and extensive customization for everyone regardless of the context or use case.
Open-source AI studio for short dramas, short videos and product ads: one-line idea → script, cast, storyboard, video, voice, edit. Self-hosted. | AI 短剧/短视频工坊
A knowledge base toolkit for research and literature review. AI agents compile papers, books and notes into a structured, densely interlinked Obsidian wiki. Built on Karpathy's llm-wiki.md: ingest/query/lint skills, controlled tag vocabulary, concept hierarchy + Canvas, arXiv->LaTeX formula pipeline, exit-code audits.
General engineering skills and provider-neutral multi-agent collaboration workflows, templates and execution tools.
Build tool-using AI agents and collaborating teams in Scala 3 and ZIO 2. Typed tools, scoped execution, explicit application control.
Open-source platform for orchestrating, governing, and safely automating AI agents across your infrastructure.
AI coding agents that run for hours without losing the plot. A foreman plans each ticket in a fresh session, a cheap model does the heavy coding, another model family inspects it, and you merge only what comes with proof. Your Claude Code limit goes much further.
A phone-first AI roleplay client — Character Card V2/V3, bring your own API key, local-only.
🧸 Put your Muse in Discord. DM it or invite it to any Discord server.
B站 收藏夹 分类 整理 智能整理器 | 「小明」AI B站收藏夹智能整理器 · 基于 DeepSeek 的油猴脚本。关键词：B站收藏夹 收藏夹分类 收藏夹整理 收藏夹管理 收藏夹 分类 整理 B站 油猴脚本 脚本 AI分类。AI/本地双模式、先预览确认再移动、失效归档/查重/备份/撤销、暖色纸质 UI。Xiaoming Bilibili Favorites Organizer, Tampermonkey userscript with DeepSeek.
Local studio to plan new products or scan existing repos: agent handoffs and codebase quality reports, on your machine.
软协小软 —— 软件协会（CSUFT）技术助手 QQ 机器人。基于 Kondius/qq-agent 定制：容器化部署、连续对话窗口、角色卡权重修正
Local statistics dashboard and HTTP proxy for Gufo inference servers
Durable, replayable agentic workflows in Python: algebraic effects as composable generators, PEP 750 t-strings as typed prompt channels.
Two friends learning AI engineering, and the game we built to keep each other going: XP, quiz duels, code races and an in-browser AI lab.
Digital-rain style htop/nvtop for NVIDIA GB10 (ASUS Ascent GX10, DGX Spark): GPU, unified memory and which AI models are loaded by vLLM, Ollama, ComfyUI & co.
Let a text-only LLM (like GLM-5.3) read screenshots: an OpenAI-compatible proxy that captions images with a local Ollama vision model. Works with ZCode.
Estuda.AI: oficina da UniBH para usar um LLM dentro do seu app (chat em streaming, saída JSON validada e RAG com pgvector). FastAPI + Ollama + Docker.