SoL-Pi
by NVIDIA
Extends the Pi agent harness with AutoResearch loops from NVIDIA, improving efficiency on long-running autonomous research and coding tasks.
Skills
Research Loop
Runs iterative AutoResearch cycles that refine an approach across repeated attempts.
Harness Extension
Plugs into the Pi agent harness without replacing the existing agent loop.
Efficiency Tuning
Reduces token and step cost on long-horizon tasks through structured iteration.
Related Agents
Agent Lightning
Optimizes any AI agent with reinforcement learning without rewriting it, decoupling training from execution so existing…
Cherry Studio
Runs a Windows, Mac, and Linux desktop client for OpenAI, Gemini, Anthropic, Ollama, and LM Studio models, with 300+ pr…
Crawl4AI
Crawls and scrapes web pages into clean Markdown for RAG pipelines, with CSS, XPath, and LLM-driven structured extracti…
FastGPT
Builds AI agents on a visual Flow canvas backed by hybrid-retrieval knowledge bases, workflow and RPA nodes, bidirectio…