Alternatives and similar repositories for Toucan

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

• eval-sys / mcpmark
  MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.
  ☆378Updated last week
• RUCAIBox / R1-Searcher-plus
  R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
  ☆71Updated 8 months ago
• meituan-longcat / LongCat-Flash-Thinking-2601
  ☆229Updated 2 weeks ago
• PaperDecision / PaperDecision
  ☆169Updated 2 weeks ago
• hkust-nlp / WebExplorer
  The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"
  ☆100Updated 4 months ago
• zhangxy-2019 / critique-GRPO
  ☆56Updated 4 months ago
• antgroup / Research-Venus
  Deep Research
  ☆303Updated 5 months ago
• meituan-longcat / UNO-Bench
  Omni Model Benchmark with high quality and diversity, which reveals the Compositional Law. We’re now focused on Chinese scenarios — and a…
  ☆74Updated 3 weeks ago
• DeepSoftwareAnalytics / swe-factory
  [FSE'2026] SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
  ☆144Updated last week
• GAIR-NLP / OctoThinker
  Revisiting Mid-training in the Era of Reinforcement Learning Scaling
  ☆182Updated 6 months ago
• OSU-NLP-Group / Mind2Web-2
  [NeurIPS'25 D&B] Mind2Web-2 Benchmark: Evaluating Agentic Search with Agent-as-a-Judge
  ☆98Updated last month
• facebookresearch / sweet_rl
  Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
  ☆260Updated 9 months ago
• MiroMindAI / MiroRL
  MiroRL is an MCP-first reinforcement learning framework for deep research agent.
  ☆226Updated 5 months ago
• OpenBMB / RLPR
  Extrapolating RLVR to General Domains without Verifiers
  ☆196Updated 5 months ago
• NVlabs / Tool-N1
  ☆219Updated 8 months ago
• MIT-MI / MEM1
  ☆229Updated last month
• 1KE-JI / UPFT
  Official resources of "The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reaso…
  ☆16Updated 7 months ago
• RUCAIBox / SimpleDeepSearcher
  SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
  ☆118Updated 8 months ago
• THUDM / AgentRL
  Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
  ☆205Updated 2 weeks ago
• open-compass / GTA
  [NeurIPS 2024 D&B Track] GTA: A Benchmark for General Tool Agents
  ☆133Updated 10 months ago
• RM-R1-UIUC / RM-R1
  RM-R1: Unleashing the Reasoning Potential of Reward Models
  ☆158Updated 7 months ago
• LLM360 / Reasoning360
  A repo for open research on building large reasoning models
  ☆133Updated last week
• MiniMax-AI / SynLogic
  [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
  ☆191Updated 6 months ago
• test-time-interaction / TTI
  ☆72Updated 7 months ago
• ByteDance-BandAI / ReportBench
  A comprehensive benchmark for evaluating deep research agents on academic survey tasks
  ☆49Updated 5 months ago
• zhenyuhe00 / SWE-Swiss
  SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution
  ☆104Updated 4 months ago
• sunnweiwei / FoldAgent
  Scaling Long-Horizon LLM Agent via Context-Folding
  ☆106Updated last week
• MTU-Bench-Team / MTU-Bench
  MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models
  ☆58Updated 6 months ago
• ReasoningTransfer / Transferability-of-LLM-Reasoning
  ☆108Updated last month
• KANABOON1 / MemGen
  MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
  ☆298Updated this week