Back to directory

Zenii

A local Rust AI backend that runs as one daemon so a desktop app, CLI, TUI, scripts and MCP clients all share the same memory, tools, providers and scheduler through one HTTP and WebSocket API.

Zenii

Zenii solves the problem of AI tools that keep separate, per-session context by running a single local daemon that every interface talks to: a desktop app, a CLI, a terminal UI, shell scripts and MCP clients all read and write the same memory, credential store and tool registry rather than each re-implementing their own. The daemon exposes a built-in, browsable API explorer with live request testing and code-snippet generation once it is running.

One Rust library crate holds all business logic, and five thin binary crates, a daemon, CLI, TUI, desktop app and MCP server, are shell wrappers around the same gateway, SQLite database, agent loop and tool registry. Capabilities include persistent semantic memory with temporal decay and deduplication, document ingestion across formats such as PDF, DOCX, PPTX and XLSX into a knowledge graph, and 19 shared tools covering shell, file and web operations.

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.