The LLM abstraction layer for modern AI agent applications.
☆522Jul 16, 2026Updated 3 months ago
Alternatives and similar repositories for kosong
Users that are interested in kosong are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A lightweight operating system abstraction layer for agents.☆20Dec 26, 2025Updated 9 months ago
- ☆67Oct 27, 2025Updated 11 months ago
- [Archived] Legacy Python Kimi CLI, no longer maintained. Please use Kimi Code CLI: https://github.com/MoonshotAI/kimi-code☆11,414Sep 22, 2026Updated 3 weeks ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,010Sep 15, 2026Updated last month
- Verify Precision of all Kimi K2 API Vendor☆594Feb 14, 2026Updated 8 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆1,617Nov 17, 2025Updated 11 months ago
- ☆82Jun 20, 2025Updated last year
- Kimi Agent SDK provides a programmatic interface to interact with the Kimi CLI☆577May 29, 2026Updated 4 months ago
- ☆39Aug 4, 2025Updated last year
- Our library for RL environments + evals☆4,716Updated this week
- The filesystem for agents.☆3,475Updated this week
- Agentic RL Training at Scale☆2,172Updated this week
- A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular…☆589Sep 4, 2026Updated last month
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,429Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.☆5,183Feb 16, 2026Updated 8 months ago
- DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL☆348Jun 17, 2026Updated 4 months ago
- Muon is Scalable for LLM Training☆1,548Aug 3, 2025Updated last year
- VibeRL is a Reinforcement Learning framework built essentially through vibe coding with Kimi K2.☆18Updated this week
- Tongyi Deep Research, the Leading Open-source Deep Research Agent☆20,053Feb 27, 2026Updated 7 months ago
- Trae Agent is an LLM-based agent for general purpose software engineering tasks.☆12,145Feb 5, 2026Updated 8 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,159Updated this week
- The absolute trainer to light up AI agents.☆18,745Oct 9, 2026Updated last week
- A Gym for Agentic LLMs☆510Jan 21, 2026Updated 8 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Streamline on-policy/off-policy distillation workflows in a few lines of code☆111Aug 5, 2026Updated 2 months ago
- open-source coding LLM for software engineering tasks☆1,356Sep 30, 2025Updated last year
- A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents.☆3,057Feb 14, 2026Updated 8 months ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,281Sep 1, 2026Updated last month
- Renderer for the harmony response format to be used with gpt-oss☆4,529Apr 8, 2026Updated 6 months ago
- A high-level multi-agent development framework built on LangGraph, combining CrewAI’s intuitive concepts with enterprise-grade features, …☆117Aug 18, 2026Updated 2 months ago
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,807Updated this week
- Bub it. Build it. A tiny agent runtime, composable with plugins.☆1,686Updated this week
- Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"☆611Nov 4, 2025Updated 11 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Kimi K2 is the large language model series developed by Moonshot AI team☆11,112Jan 21, 2026Updated 8 months ago
- Kimi Code CLI — The Starting Point for Next-Gen Agents☆7,924Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,821Updated this week
- ☆18Jun 3, 2025Updated last year
- slime is an LLM training framework for RL Scaling.☆8,682Updated this week
- ☆123Feb 4, 2026Updated 8 months ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,841Updated this week