#59 · Primary category: LLM Application Frameworks
agent-native
A framework for building agent-native applications.
Project last updated:08/30/26
GitHub Stars
4.6K
Forks
436
Contributors
66
License
Other
Why we included this project
Agent-Native treats one piece of work as the core unit: you define an action once and it becomes available to the web UI, an agent, an HTTP endpoint, MCP, A2A, and a CLI at the same time. So a team can ship a single codebase that serves both people and AI agents, instead of maintaining separate integrations for each surface. The bundled agent runtime covers chat, tools, skills, memory, jobs, observability, and handoffs, and the framework stays backend-agnostic, letting you plug in any Drizzle-supported SQL database and Nitro-compatible host. That combination suits developers and small teams who are already building an app and want the agent layer to reuse the same logic rather than sit beside it. Starter templates show how the pieces fit together before you start customizing.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform