1microsoft / markitdown
Python tool for converting files and office documents to Markdown.
+1,241 stars
from 192,172 · score 7.12
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
21 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2headroomlabs-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.
+754 stars
from 77,813 · score 6.63
3StarTrail-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.
+639 stars
from 13,106 · score 6.46
4BerriAI / 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]
+469 stars
from 62,030 · score 6.15
5bytedance / 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.
+423 stars
from 84,416 · score 6.05
6langchain-ai / langgraph
Build resilient agents.
+402 stars
from 43,884 · score 6.00
7langchain-ai / langchain
The agent engineering platform.
+393 stars
from 148,446 · score 5.98
8langchain-ai / deepagents
The batteries-included agent harness.
+286 stars
from 30,578 · score 5.66
9comet-ml / opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
+179 stars
from 22,919 · score 5.19
10Cygnux-Labs / Tracekit
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
+125 stars
from 234 · score 4.84
11Arize-ai / phoenix
AI Observability & Evaluation
+96 stars
from 11,999 · score 4.57
12mlflow / 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.
+87 stars
from 28,531 · score 4.48
131Panel-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。
+52 stars
from 23,035 · score 3.97
14EmbraceAGI / 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! 🚀
+10 stars
from 11,784 · score 2.40
15chatchat-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
+7 stars
from 38,704 · score 2.08
16zilliztech / GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
+3 stars
from 8,216 · score 1.39
17OpenGVLab / Ask-Anything
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
+3 stars
from 3,362 · score 1.39
18OWASP / 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.
+3 stars
from 190 · score 1.39
19aiqualitylab / 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.)
+2 stars
from 25 · score 1.10
20mthamil107 / 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.
+2 stars
from 17 · score 1.10
21NameetP / 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.
+1 stars
from 85 · score 0.69