Model VS AI Radar

Open AI projects

This index tracks active public AI repositories. It separates repository popularity from quality: a seven-day change is calculated only from saved weekly GitHub star snapshots.

Current source snapshot

100 verified source records in this snapshot. Updated . Source: GitHub Repository Search API.

Method: Seven-day growth is the difference between verified weekly repository star snapshots.

Limits: Repository stars and forks are public popularity signals, not an assessment of software quality, security, or fitness for a particular use.

Representative records from this snapshot

orca

Source identity: stablyai/orca

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

Recorded signal: 72,165 GitHub stars; +5,197 in 7 days
Source date:

WeKnora

Source identity: Tencent/WeKnora

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Recorded signal: 27,138 GitHub stars; +4,671 in 7 days
Source date:

hermes-agent

Source identity: NousResearch/hermes-agent

The agent that grows with you

Recorded signal: 246,991 GitHub stars; +2,283 in 7 days
Source date:

iFixAi

Source identity: ifixai-ai/iFixAi

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less t…

Recorded signal: 15,596 GitHub stars; +1,603 in 7 days
Source date:

langwatch

Source identity: langwatch/langwatch

The platform for LLM evaluations and AI agent testing

Recorded signal: 4,816 GitHub stars; +1,285 in 7 days
Source date:

minimind

Source identity: jingyaogong/minimind

🧠 Train a 64M-parameter LLM from scratch in just 2h!

Recorded signal: 61,639 GitHub stars; +871 in 7 days
Source date:

vllm

Source identity: vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Recorded signal: 92,143 GitHub stars; +598 in 7 days
Source date:

litellm

Source identity: BerriAI/litellm

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI…

Recorded signal: 59,126 GitHub stars; +580 in 7 days
Source date:

langchain

Source identity: langchain-ai/langchain

The agent engineering platform.

Recorded signal: 146,640 GitHub stars; +470 in 7 days
Source date:

langflow

Source identity: langflow-ai/langflow

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

Recorded signal: 155,000 GitHub stars; +383 in 7 days
Source date:

airllm

Source identity: lyogavin/airllm

AirLLM 70B inference with single 4GB GPU

Recorded signal: 34,540 GitHub stars; +362 in 7 days
Source date:

sglang

Source identity: sgl-project/sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

Recorded signal: 36,161 GitHub stars; +321 in 7 days
Source date:

Explore the interactive index to search and sort all 100 records. Each title links to its original source record.