AI Agents & LLM Frameworks Telemetry Index

Relay-site attributed token usage for DeepSeek Harness — zero config, no credentials

JarvisCore is a runtime where AI agents operate as a fleet of equal peers. Agents discover one another by capability, execute tasks from a shared ledger, and authenticate to every external service through a zero-trust broker, never with their own keys.

A simple, yet handy, LLM gateway.

Golem — The self-evolving GeoAI Agent for the geospatial industry — natural-language GDAL/PostGIS workflows, learned pipeline reuse, fabricated tool scaffolding, approval & audit governance, accessible via WebUI, TUI, and IM channels.

Dual AI Collaboration Framework Builder - Establish clear division of labor between Claude + Codex

An LLM programming assistant engine built with Go, supporting WebSocket, multi-turn dialogues, tool calling, permission control, and skill extension.

Go CLI A coding agent for your terminal, written in Go. Explore a codebase, edit files and run commands through an interactive UI or a scriptable CLI.

NextJS AI Web Everyone can become a director. The Nextjs front-end of an AI driven platform for automatic movie/video generation (form GPT script generation to text2video movie generation). AI GPT

(VillagerAgent ACL 2024) A Graph based Minecraft multi agents framework

RAG PDF Agent scope FastAPI + Vue3

Kakobuy Spreadsheet features 3,000+ trending products from Weidian, Taobao, and 1688, with affordable new arrivals added daily. Explore the latest finds from the past 7 days, plus shoes and clothing on MaisonLooks with QC photos and AI try-on. Order easily through your preferred agent.

Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Perspective

LangGraph AI 62+ Manus Agent SSE

Containerized desktop environment and virtual GUI runtime for autonomous computer-use AI agents.

Claw-style Bot in Your Mobile Device

3DMed-RAG query RAG llm VQA-MedRAG - Multimodal-RAG index

Kubernetes-native framework for bot and scraper orchestration

Multi-agent AI article generation system based on LangGraph & DeepAgents, with RAG retrieval, hallucination suppression, parallel writing and context management.

LLM-zero2hero developer tool

Abp.vNext + EF Core The microservices Open source framework project supports the implementation of message push workflow certification centers based on OAuth2.0

Enterprise-grade Next-Generation AI Agent Infrastructure

[NeurIPS 2026] State of Thought Enables Endogenous Reasoning

Autonomous JavaScript AI agent and orchestration framework for workers sub workflows.

Autonomous Python AI agent and orchestration framework for EasyRAG workflows.

Telethon Telegram (WebUI) / Perfect for OSINT, TG marketing, and auto-reply agents.

proxyless-llm-websearch developer tool

🎬 Claude Code skill for showreel-grade, beat-synced motion graphics with HyperFrames (HTML + GSAP + SVG + Canvas, Apache-2.0) — 120 BPM / 60 FPS to MP4

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to runnable code, swap wire protocols (Dify/OpenAI).

The open source Agent Harness with a Company Brain. Self-hosted AI Agents for Slack, Teams, Lark, DingTalk, WeCom, and more. An open source alternative to Claude Tag.

High-fidelity Codex UI plugin and developer workspace interface built on DeepSeek Harness.

wxauto bot for java spring ai and DDD

[ACL 2025] The code repository for "Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning" in PyTorch.

Git for AI Agent Knowledge. A persistent, versioned memory layer for AI systems. Hybrid GraphRAG retrieval. Runs entirely offline.

Open-source model-agnostic runtime for AI agents to perceive, understand and operate computers and mobile environments.

VLM VLA A curated collection for multimodal intelligence research, covering VLMs, VLAs, World Models, and embodied AI tracking next-generation agent technologies from perception to decision-making, with a focus on papers, code, and datasets.

SecureJS JavaScript AKSK DeepSeek

A minimalist multi-agent framework for rubost automation of scientific analysis workflows, such as gene expression analysis.

Prompt Learning using Metaheuristics

Transform ChatGPT into a navigable knowledge graph. Visualize complex branches with the spatial Graph View, manage history via the Git-style Timeline Tree, and enjoy a growing toolkit of workflow utilities.

CodeNight Starter — An open-source foundation for building modern web applications. Built on industry standards with Next.js, shadcn/ui, Better Auth, Prisma, and PostgreSQL, and designed to be customized for your brand and workflow.

+RAG (Vue3+FastAPI+Milvus+DeepSeek/ / )

🌀 AI Inspiration Capture — Browser Extension + Telegram Bot + Web Dashboard

Multi-agent adversarial debate framework where 11 specialized AI units cross-validate claims with confidence scores.

One Developer. An Entire Fleet of Autonomous Coding Agents. Local-first desktop agent workbench built on Electron + pi.

Autonomous Python AI agent and orchestration framework for MyArxiv Agent workflows.

Z.ai's coding agent harness. Powerful, intelligent, extensible.

An out-of-the-box local Web UI for DeepSeek-OCR. Built with FastAPI + Vue.js, it supports PDF/Image uploads, progress tracking, and result visualization with bounding boxes. Easily experience the power of a top-tier OCR model.

An AI agent command-line interface — multi-model LLM access, streaming terminal UI, tool calling, permission control, and session persistence.

A powerful terminal coding agent based on Claude Agent SDK. Better then Claude Code when start up a new project, or u have no idea. Just try it.

Lightweight runtime safety guard for multimodal LLM I/O

Approvable, local-first AI coding agent for regulated teams.

A Laravel package for versioned AI prompt management with variable interpolation, performance tracking & A/B testing.

Superpowers skills for DeepSeek Harness: TDD, debugging, planning, and collaboration skills adapted from obra/superpowers

Persistent memory for AI agents, for code, research and everyday life. Facts are typed, sourced, and retired when they change. Local SQLite, no API keys.

DORA (Data Oriented Report Automator) automates Exploratory Data Analysis (EDA) to help you effortlessly explore datasets. Generate insightful statistics, visualizations, and reports with just a click! Streamline your data exploration workflow and uncover trends, patterns, and relationships in your data with ease.

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

Open-source AI coding desktop app with parallel agents and persistent project memory. Local models, Ollama or cloud AI. Windows, macOS and Linux.

LLM GPU/NPU TTS An Android LLM chat assistant that lets you download and manage your own models. Customize character personas, and switch seamlessly between on-device inference (with GPU/NPU acceleration on supported devices) and cloud-based models. Built-in

flash loan arbitrage bot in EVM chain three Dex - uniswap, camelot and aerodrome

Deploy, monitor, and tune LLM through a visual interface — plus image / video generation on top of ComfyUI.