Back to directory

Osaurus

A native macOS AI harness that keeps agents, memory, tools and identity on a user's own Mac, running fully offline in Swift with no Electron.

Osaurus

Osaurus is an AI harness for macOS that sits between the user and any model, local or cloud, providing the continuity of context, memory, tools and identity that makes AI feel personal rather than resetting each session. It works fully offline with local models, and can also connect to any cloud provider when more power is wanted, with nothing leaving the Mac unless the user chooses.

Agents are the core of the app: each one has its own prompts, memory and visual theme, and tools and skills are selected automatically through RAG search based on the task at hand, without manual configuration. Agents can opt into a private local database and a single self-scheduled next run, with local storage in plaintext by default (protected by FileVault) or optionally encrypted with SQLCipher.

It installs via Homebrew or a downloadable .dmg, in a standard build or a larger one bundling a default model, and is built natively in Swift for Apple Silicon under the MIT license.

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.