Open-source LLM apps and frameworks

PallasBot

Pallas-Bot

★ 490

An Arknights (Pallas) group-chat bot that echoes whatever members say, paired with an LLM to be the "Niuniu" that knows you best.

phoenix-zhou

multi-agent

★ 490

A multi-agent travel assistant system built using the **Agent2Agent (A2A)** protocol and **MCP (Model Context Protocol)**

openaccountants

openaccountants

★ 489

Open-source Tax Guides for AI agents, reviewed by named CPAs/CAs/EAs. 1,000+ Guides across 190+ jurisdictions. MCP server included. Works with Claude, ChatGPT, Cursor.

yuting0624

antigravity-for-claude-code

★ 489

Claude Code plugin: run the Antigravity CLI (Gemini) as a collaborating sub-agent with intelligent model routing across the SDLC. Community project; not affiliated with Google/Anthropic.

Licoy

GoAmzAI

★ 488

A self-hosted AIGC platform for individuals, teams and enterprises, built with Golang, Vue3 and NaiveUI. Supports AI chat, image, video and music generation, an infinite-canvas workflow, AI slide decks, mind maps, an app marketplace, and multi-user/multi-model aggregation management.

RMA-MUN

RAGNotebook

★ 488

A RAG project built with LangChain, FastAPI and React. The main branch is a knowledge-graph-based knowledge management platform; the base-rag branch is a ready-to-use basic RAG project for learning.

tizzy916

humanities-writing-companion

★ 488

End-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/Chinese), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation.

appautomaton

latex-arxiv-SKILL

★ 487

A highly customizable agentic harness for arXiv-ready ML/AI review papers (and beyond). It drives agentic AI like Codex CLI and Claude Code through a gated LaTeX workflow with verified BibTeX citations.

aws-samples

bedrock-engineer

★ 487

Universal AI Agent using Amazon Bedrock, capable of customize to create/edit files, execute commands, search the web, use knowledge base, use multi-agents, generative images and more.

Claw-Company

clawcompany

★ 487

Open source AI company OS. 38 roles, 6 templates, 4-layer memory. Your AI company remembers everything — locally. npx clawcompany

HUST-AI-HYZ

MemoryAgentBench

★ 487

Open source code for ICLR 2026 Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

jatinkrmalik

LLMFeeder

★ 487

Browser extension to convert web pages to clean Markdown and copy to clipboard so you can feed it to your favorite LLM model as context with just 1 click!

PrismorSec

prismor

★ 487

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

TilmanGriesel

chipper

★ 487

✨ AI interface for tinkerers (Ollama, Haystack RAG, Python)

baidu-baige

LoongFlow

★ 486

LoongFlow is an expert-grade Agent framework for Loop Engineering. Through a Plan-Execute-Summary loop and structured experiential memory, it enables AI to continuously think, execute, reflect, and evolve across complex software engineering, mathematical, and machine learning tasks.

dongri

openai-api-rs

★ 486

OpenAI API client library for Rust (unofficial)

RyjoxTechnologies

Octopoda-OS

★ 486

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

taovc

pr-cockpit

★ 486

Local AI PR workbench — Claude/Codex review in isolated git worktrees, human-gated GitHub comments

edouard-claude

snip

★ 485

CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.

juyterman1000

entroly

★ 485

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

mudler

vllm.cpp

★ 485

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-aware scheduling, ...)

QuZhan51496

paper2anything

★ 485

An agent skills pack that turns an academic paper PDF into slides, a poster, a webpage, a Xiaohongshu post, or a WeChat article (paper2slides/poster/html/xhs/wechat)

taylorsatula

mira-OSS

★ 485

This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure when dropped into tools/ folder, and the system prompt composes from modular trinkets. I would like to think I've made an elegant brain-in-box. You load it and send cURL requests - it talks back, learns, and uses tools. Contributions welcome.

AIScientists-Dev

Flowtrace

★ 484

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.