Alternatives and similar repositories for instinct

Users that are interested in instinct are comparing it to the libraries listed below

• benchflow-ai / benchflow
  AI benchmark runtime framework that allows you to integrate and evaluate AI tasks using Docker-based benchmarks.
  ☆165Updated 6 months ago
• sankalp1999 / code_qa
  RAG on codebases using treesitter and LanceDB
  ☆264Updated last year
• Aider-AI / polyglot-benchmark
  Coding problems used in aider's polyglot benchmark
  ☆192Updated 11 months ago
• ozyyshr / RepoGraph
  Enhancing AI Software Engineering with Repository-level Code Graph
  ☆228Updated 7 months ago
• SWE-agent / SWE-ReX
  Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
  ☆376Updated this week
• RepoUnderstander / RepoUnderstander
  Official implementation of paper How to Understand Whole Repository? New SOTA on SWE-bench Lite (21.3%)
  ☆95Updated 8 months ago
• kortix-ai / fast-apply
  ☆372Updated 2 months ago
• grapeot / deep_research_agent
  An Agentic Deep Research Assistant similar to Gemini and OpenAI Deep Research
  ☆125Updated 9 months ago
• jina-ai / node-serp
  LLM-as-SERP
  ☆70Updated 8 months ago
• coderabbitai / ast-grep-essentials
  Community-led collection of essential ast-grep rules.
  ☆110Updated 4 months ago
• MoonshotAI / kosong
  The LLM abstraction layer for modern AI agent applications.
  ☆464Updated this week
• adityasoni9998 / OpenHands-Versa
  Code for the paper "Coding Agents with Multimodal Browsing are Generalist Problem Solvers"
  ☆92Updated last month
• All-Hands-AI / openhands-aci
  Agent computer interface for AI software engineer.
  ☆114Updated 2 months ago
• babelcloud / LLM-RGB
  LLM Reasoning and Generation Benchmark. Evaluate LLMs in complex scenarios systematically.
  ☆163Updated 6 months ago
• llllvvuu / instant_apply
  proof-of-concept of Cursor's Instant Apply feature
  ☆85Updated last year
• wangxj03 / code-splitter
  Split code into semantic chunks
  ☆52Updated last year
• twitchax / augre
  An LLM-powered (CodeLlama or OpenAI) local diff code review tool.
  ☆41Updated last year
• Xuanwo / acp-claude-code
  The ACP implementation for Claude Code
  ☆239Updated 2 months ago
• lmarena / p2l
  Prompt-to-Leaderboard
  ☆261Updated 6 months ago
• qdrant / demo-code-search
  ☆55Updated 8 months ago
• open-responses / open-responses
  Self-hosted alternative to OpenAI's Responses API compatible with Agents SDK and works with all model providers (Claude/R1/Qwen/Ollama et…
  ☆102Updated 7 months ago
• justinlietz93 / agent_tools
  Agent tools CLI platform.
  ☆128Updated 2 months ago
• SecretiveShell / MCP-searxng
  MCP server for connecting agentic systems to search systems via searXNG
  ☆107Updated 9 months ago
• Aider-AI / aider-swe-bench
  Harness used to benchmark aider against SWE Bench benchmarks
  ☆78Updated last year
• yilinjz / astchunk
  ASTChunk is a Python toolkit for code chunking using Abstract Syntax Trees (ASTs), designed to create structurally sound and meaningful c…
  ☆111Updated 5 months ago
• substratusai / sandboxai
  Run AI generated code in isolated sandboxes
  ☆125Updated 9 months ago
• aymeric-roucher / GAIA
  Beating the GAIA benchmark with Transformers Agents. 🚀
  ☆138Updated 9 months ago
• NL2Code / CodeR
  ☆160Updated last year
• Kyle-Lyu / data-efficient-finetuning
  Data-efficient LLM Fine-tuning for Code Generation [IJCNN2025]
  ☆32Updated 7 months ago
• modelscope / MCPBench
  The evaluation benchmark on MCP servers
  ☆226Updated 2 months ago