Back to directory

Turing AI Agent

A modular local AI agent built with Python and Ollama that calls tools, keeps persistent memory in SQLite, searches the web, and retrieves information from documents with a lightweight RAG pipeline.

Turing AI Agent

Turing AI Agent is a locally running agent that pairs Ollama and the Qwen 2.5 model with a dynamic tool registry, giving it a calculator, current weather and time-zone lookups, web search through Tavily, persistent memory in SQLite, document reading and retrieval-augmented generation over supported files such as text, Markdown, JSON, CSV, PDF and DOCX.

Its architecture keeps tools separate from the main agent loop through the registry, which routes a user request through the local model to the appropriate tool and back, and the project includes runtime logging, error handling and an automated test suite covering the calculator, document reader, memory and web-search components.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.