Alternatives and similar repositories for DE-Bench

Users that are interested in DE-Bench are comparing it to the libraries listed below

• plastic-labs / honcho
  The Identity layer for the agentic world
  ☆189Updated this week
• Globe-Engineer / globot
  Globot is an agent that controls your browser using playwright and GPT-4V.
  ☆133Updated last year
• jxnl / blog
  ☆134Updated last week
• mendableai / data-connectors
  LLM-ready data connectors
  ☆78Updated 11 months ago
• definitive-io / openassistants
  Build robust, production grade function calling assistants that work. Declarative and extensible. Built on top of LangChain ⚡️
  ☆77Updated 11 months ago
• advaitpaliwal / reminisc
  Personal memory for AI
  ☆58Updated 11 months ago
• jmanhype / dspy-self-discover-framework
  Leveraging DSPy for AI-driven task understanding and solution generation, the Self-Discover Framework automates problem-solving through r…
  ☆60Updated 10 months ago
• yasyf / anthropic-computer-use-modal
  Anthropic Computer Use with Modal Sandboxes
  ☆34Updated 6 months ago
• definitive-io / human-eval-sampling-benchmark
  OpenAI's human-eval sampling benchmark
  ☆13Updated last year
• yoheinakajima / quick_email_scripts
  A couple scripts to grab stats from email
  ☆42Updated 8 months ago
• pippinlovesyou / pippin-lite
  a minimalistic template for dynamic self-building AI agents
  ☆97Updated 3 months ago
• mendableai / rag-arena
  Open-source RAG evaluation through users' feedback
  ☆182Updated last year
• markokraemer / mirko.ai
  ☆30Updated 10 months ago
• agentsea / surfkit
  A toolkit for building computer use AI agents
  ☆160Updated this week
• hellovai / ai-that-works
  🦄 ai that works - every tuesday 10 AM PST
  ☆70Updated this week
• jose-mdz / draw-and-guess
  Use of vision models to play a "pictionary" style draw-guessing.
  ☆43Updated 7 months ago
• jlewi / foyle
  Foyle is a copilot to help developers deploy and operate their applications.
  ☆128Updated 2 months ago
• JeezAI / DSPy_matchmaking
  A seamless matchmaking application that is programmed with Cohere Command R+, Stanford NLP DSPy framework, Weaviate Vector store and Crew…
  ☆59Updated last year
• browserbase / browserbase-computer-use
  A collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API
  ☆44Updated 6 months ago
• homanp / nagato
  🌸 The open framework for question answering fine-tuning LLMs on private data
  ☆69Updated last year
• Scrapybara / scrapybara-cookbook
  Example code and guides for building with Scrapybara
  ☆130Updated last month
• Globe-Engineer / handkerchief
  Globe Engineer - Handkerchief: A higher quality alternative to vector database RAG.
  ☆24Updated last year
• nuwandavek / karpathify
  ☆93Updated 7 months ago
• run-llama / ts-playground
  ☆61Updated last year
• OneInterface / what-did-i-do-today-gpt4v
  ☆72Updated last year
• Scrapybara / scrapybara-python
  Scrapybara Python SDK
  ☆64Updated last month
• hdresearch / nolita
  Work with web-enabled agents quickly — whether running a quick task or bootstrapping a full-stack product.
  ☆93Updated 6 months ago
• PaymanAI / langman-examples
  A repository Payman + Langgraph integration examples that allow AI Agent to simply create tasks for Humans on Payman that pay them money …
  ☆82Updated 7 months ago
• Glavin001 / Alvea-AI
  AI assistant that Intuitively Adapts to You
  ☆81Updated last year
• stableagents / stableagents
  Standardized gateway, debugging and multi-authentication client for MCP
  ☆44Updated this week