ByteDance-Seed / Seed-CoderLinks
Seed-Coder is a family of lightweight open-source code LLMs comprising base, instruct and reasoning models, developed by ByteDance Seed.
☆738Updated 7 months ago
Alternatives and similar repositories for Seed-Coder
Users that are interested in Seed-Coder are comparing it to the libraries listed below
Sorting:
- The official repository of the dots.llm1 base and instruct models proposed by rednote-hilab.☆487Updated 5 months ago
- OpenCUA: Open Foundations for Computer-Use Agents☆661Updated 2 weeks ago
- ☆520Updated last month
- [ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction☆566Updated 8 months ago
- open-source coding LLM for software engineering tasks☆1,113Updated 4 months ago
- ☆865Updated 4 months ago
- ☆814Updated 7 months ago
- ZeroSearch: Incentivize the Search Capability of LLMs without Searching☆1,236Updated 5 months ago
- ☆871Updated 5 months ago
- MCP-Zero: Active Tool Discovery for Autonomous LLM Agents☆443Updated 7 months ago
- Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.☆833Updated last month
- ☆1,222Updated 3 months ago
- A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.☆875Updated 6 months ago
- ☆1,282Updated 2 weeks ago
- Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving☆415Updated 5 months ago
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆618Updated last week
- AgentFlow: In-the-Flow Agentic System Optimization☆1,543Updated last week
- Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"☆558Updated 3 months ago
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆673Updated 10 months ago
- SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasonin…☆227Updated 4 months ago
- The LLM abstraction layer for modern AI agent applications.☆499Updated last week
- ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.☆623Updated last week
- Unleashing the Power of Reinforcement Learning for Math and Code Reasoners☆741Updated 7 months ago
- Ling is a MoE LLM provided and open-sourced by InclusionAI.☆238Updated 8 months ago
- AgentEvolver: Towards Efficient Self-Evolving Agent System☆1,109Updated last week
- An Open-Source Large-Scale Reinforcement Learning Project for Search Agents☆546Updated 2 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆468Updated 8 months ago
- The evaluation benchmark on MCP servers☆236Updated 5 months ago
- ☆910Updated last month
- [EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking☆489Updated 5 months ago