Currents
Signals, tools, projects, tensions, and early patterning from the open source AI ecosystem.
Public record for open source AI
Openflows documents the open source AI ecosystem as a field in motion: tools lowering barriers to inference and orchestration, models circulating as shared infrastructure, governance experiments running in public, and practitioners shaping direction through sustained work.
This knowledge base is maintained by Peng (鵬), an agent named from Zhuangzi's Inner Chapters. Peng monitors signals, drafts entries, and identifies emerging patterns, proposing rather than publishing, with human review at every threshold. The site is the record; Peng keeps it current.
Signals, tools, projects, tensions, and early patterning from the open source AI ecosystem.
Synthesized patterns that have stabilized across multiple currents.
People whose sustained practice makes the field more legible.
Superset is an Electron-based desktop orchestration tool that runs multiple CLI coding agents in parallel using isolated git workspaces.
LightRAG is an open-source retrieval-augmented generation framework optimized for speed and simplicity, utilizing knowledge graph structures to enhance context retrieval efficiency.
Aider is a command-line interface tool that enables AI-assisted code editing, refactoring, and explanation directly within the terminal environment using repository context.
gptme is a Python-based command-line interface tool that facilitates persistent autonomous agent sessions with local tool integration and multi-provider LLM support.
holaOS is an Electron-based desktop environment designed to provide persistent runtime, memory, and state management for autonomous agents operating over long-horizon workflows.
An Android application enabling offline local inference of quantized LLMs via ONNX Runtime and LiteRT backends for mobile hardware.
Paseo is a remote orchestration tool for AI coding agents that enables control across mobile, desktop, and CLI interfaces.
A Python-based agentic infrastructure for integrating large language models with multi-platform instant messaging services through a plugin architecture.
PaddlePaddle's high-performance inference and deployment toolkit for LLMs and VLMs, featuring specialized quantization methods and OpenAI-compatible serving protocols.
Multica is an open-source orchestration engine designed to enable autonomous AI agents to share, reuse, and compound skills across distributed workflows.
A native macOS AI assistant built with Swift and SwiftUI that prioritizes local data processing and supports multiple AI providers for autonomous task execution.
A modular Java SDK that unifies multi-provider LLM access, agentic runtime execution, and RAG pipelines for JDK 8+ environments.
currency/search-index.json provides the public search index used by this site.knowledge-manifest.json provides the complete knowledge base with body content and metadata.