AI Agents & LLM Frameworks Telemetry Index

An Open Agent Computer for ANY digital work.

FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and drive tools, with cost-aware routing across LLM providers.

System of record for how agents build software: Built-in rust harness & 20+ CLIs.

LLM-powered conversational data analysis agent that generates interactive visualizations and business insights without SQL.

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

RPent: Agentic Infrastructure for the Physical World

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.

Automated video and media editing deck powered by multimodal LLM scene analysis.

World2Agent(W2A) is an open protocol that standardizes how Al agents perceive the real world.

Lightweight hierarchical long-term memory engine for LLM conversational agents.

Local-first accounting and transaction audit agent with double-entry ledger verification.

Build agent that uses 80% less token and delivers better results.

🖥️ GUI AI Claude Gemini Codex Copilot Kiro

A highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of AI capabilities such as LLM, AI Chat, RAG, and Agents.

An evidence-led, six-language LLM playbook: the transferable core, the Codex flagship track, and adapters for ChatGPT, Claude Code, Gemini, DeepSeek, and Grok.

OpenABCode is a coding agent that dynamically routes development tasks to the best-suited models

WebGPU ocean skin for DeepSeek Harness — DSH plugin, Harness-only Chrome/Edge extension, static installer, and native integration.

The command center for AI agents such as Claude Code, Codex, and Gemini-Cli, making your agents ten times more efficient.

The open-source Devin alternative. Run Claude Code, Codex or OpenCode in isolated cloud workspaces you can self-host.

MathLens Agent Skill Manim 1-10 0.2-1

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.

You don't need a chat ui but a canvas with ai.

Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.

Shunt Claude Code agents to any model — selective, per-agent inference-layer routing proxy

High Performance KV Cache for LLM Inference

Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat — with any LLM provider.

Harnessclaw is a powerful, Electron-based desktop application designed to manage, chat with, and operate AI agents and skills seamlessly.

Autonomous Python AI agent and orchestration framework for qaa airtype workflows.

An open protocol for discovering A2A-capable AI agents on local networks — the discovery & trust bootstrap layer beneath A2A (mDNS/DNS-SD, well-known endpoints, signed AgentCards).

macOS app for 24/7 AI agents in an IDE with memory, scheduled tasks, browser use + access to Whatsapp, Telegram, Slack.

[NeurIPS'26] Official Implementation for AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent(https://arxiv.org/abs/2602.03955)

wazuh azure security-operations siem mistral llm hipaa terraform aks mlops soc open-source azure-api-management lora fine-tuning

`xxg-portrait-rebuild-light` is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and background atmosphere with a director-led lighting workflow while restoring clean, healthy, low-contrast photographic skin microtexture.

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.

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

Rubric-oriented document set evaluation and selection for RAG.

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

RAG PDF Agent scope FastAPI + Vue3

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

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

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

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

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

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).

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.

Autonomous AI copilot and orchestration runtime for multi-model developer workflows.

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

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

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

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

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.

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

Chrome extension & web tool to format/compress prompt content between escaped line text and readable Markdown

OpenTelemetry-native LLM observability CLI. Point any OTEL exporter at it and watch your LLM/agent traces in real time.

[ACL 2026] Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning