1.microsoft / markitdown
Python tool for converting files and office documents to Markdown.
+23,116 stars
from 170,297 · score 10.05
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
23 repositories by Attention Score · Aug 5, 2026 – Nov 2, 2026 (UTC)
2.headroomlabs-ai / headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
+14,587 stars
from 63,980 · score 9.59
3.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, vLLM, Nvidia NIM]
+7,353 stars
from 55,146 · score 8.90
4.bytedance / deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
+6,181 stars
from 78,658 · score 8.73
5.langchain-ai / langchain
The agent engineering platform.
+6,144 stars
from 142,695 · score 8.72
6.langchain-ai / langgraph
Build resilient agents.
+5,614 stars
from 38,672 · score 8.63
7.langchain-ai / deepagents
The batteries-included agent harness.
+3,704 stars
from 27,160 · score 8.22
8.comet-ml / opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
+2,118 stars
from 20,980 · score 7.66
9.mlflow / mlflow
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.
+1,343 stars
from 27,275 · score 7.20
10.Arize-ai / phoenix
AI Observability & Evaluation
+1,254 stars
from 10,841 · score 7.13
11.StarTrail-org / LEANN
[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
+1,048 stars
from 12,697 · score 6.96
12.1Panel-dev / MaxKB
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
+810 stars
from 22,277 · score 6.70
13.chatchat-space / Langchain-Chatchat
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
+364 stars
from 38,347 · score 5.90
14.EmbraceAGI / awesome-chatgpt-zh
ChatGPT 中文指南🔥，ChatGPT 中文调教指南，指令指南，应用开发指南，精选资源清单，更好的使用 chatGPT 让你的生产力 up up up! 🚀
+226 stars
from 11,568 · score 5.42
15.Chainlit / chainlitArchived
Build Conversational AI in minutes ⚡️
+199 stars
from 12,312 · score 5.30
16.zilliztech / GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
+126 stars
from 8,093 · score 4.84
17.OWASP / www-project-agent-memory-guard
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
+86 stars
from 107 · score 4.47
18.OpenGVLab / Ask-Anything
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
+27 stars
from 3,338 · score 3.33
19.NameetP / pdfmux
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
+9 stars
from 77 · score 2.30
20.ThreatRecall / zettelforge
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
+8 stars
from 58 · score 2.20
21.mthamil107 / prompt-shield
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
+7 stars
from 12 · score 2.08
22.aiqualitylab / ai-natural-language-tests
Enterprise-grade platform to generate and execute Cypress, Playwright, WebdriverIO, and Appium end-to-end tests from natural language requirements. (Appium is experimental and requires external mobile infrastructure.)
+5 stars
from 22 · score 1.79
23.showlab / VLog
[CVPR 2025] Video Narration as Vocabulary & Video as Long Document
+1 stars
from 587 · score 0.69