#43 · Primary category： LLM Application Frameworks
PocketFlow
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Project last updated：07/26/26
GitHub Stars
11.1K
Forks
1.2K
Contributors
28
License
MIT
Why we included this project
Most LLM frameworks ask you to adopt a heavy runtime, but Pocket Flow keeps the whole thing to about a hundred lines. That restraint makes it easy to see exactly what your agent code does, and the graph-style building blocks cover workflow, agent, multi-agent, and RAG patterns without dragging in dependencies or locking you into a vendor. Because the source is small enough to read end to end, you can copy it straight into your project and change it however you like, which makes it useful for learning how agent pipelines fit together or for prototyping quickly. It also holds up as a teaching tool, since the whole abstraction.
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