Skip to main content
Glama
engine

engine

engine

A self-owned, model-agnostic AI agent client whose core is a native, host-agnostic plugin system. Adding a tool — from a tiny helper to the full scribe transcriber — is one small act, and the same tool works for both you (a REPL command) and the agent (a model tool). Plain line-REPL by design: no fullscreen TUI, so Polish input, trackpad scroll and text selection just work. Runtime is stdlib-only and portable (macOS now, Linux/3090 later).

Layout

  • engine/ — core: config, backends (the model interface), plugins (contract + discovery), agent (the loop), repl (the client), cli (bare-shell host adapter).

  • plugins/ — drop-in plugins: sysinfo (tiny), scribe (big). Add one = add a file here.

  • tests/ — pytest suite (deterministic, no network).

  • smoke/ — live checks against a real model (Ollama).

  • tools/check_polish_input.py — a Polish-keyboard input check.

Related MCP server: cc-plugin-mcp

Run

# REPL (talks to qwen3:8b via Ollama by default):
PYTHONPATH=. .venv/bin/python -m engine.repl
# force the deterministic mock model instead:
ENGINE_BACKEND=mock PYTHONPATH=. .venv/bin/python -m engine.repl
# run a plugin straight from the shell (no model):
PYTHONPATH=. .venv/bin/python -m engine.cli sysinfo
PYTHONPATH=. .venv/bin/python -m engine.cli scribe --help

Add a plugin (zero core edits)

Create plugins/hello.py:

from engine.plugins import SimplePlugin
PLUGIN = SimplePlugin("hello", "say hi",
    {"type": "object", "properties": {"input": {"type": "string"}}},
    lambda a: "hi " + str(a.get("input", "")))

It is now a REPL command (/hello), a CLI command, and a tool the agent can call.

Swap the model (one value)

ENGINE_BACKEND=ollama|mock|anthropic (+ ENGINE_OLLAMA_MODEL / ENGINE_ANTHROPIC_MODEL). A new provider is one branch in engine/backends.py:get_backend. (anthropic is code-complete + unit-tested for wire format; going live needs ANTHROPIC_API_KEY.)

Use the plugins inside Claude Code (MCP)

The same plugins are exposed to Claude Code via a hand-rolled MCP stdio server (stdlib, zero deps):

# from the repo root:
claude mcp add engine -- "$PWD/.venv/bin/python" -m engine.hosts.mcp_server

Then Claude Code can call sysinfo / calc / scribe as tools — the identical plugins your REPL uses.

Tests

.venv/bin/python -m pytest .                     # 36 deterministic tests
.venv/bin/python smoke/ollama_agent_smoke.py     # live: a real model calls a plugin
.venv/bin/python smoke/filter_spike.py           # Phase-2 taste: bge-m3 separates real vs junk (toy)

Available Tools

3 tools
calcB

Evaluate an exact arithmetic expression (+, -, *, /, **, %). Use for any calculation.

Inputs: expression.

scribeA

Run the scribe CLI (video -> transcript for AI). Pass CLI arguments, e.g. args=['--help'] or args=['', '--dry-run', '--json'].

Inputs: args.

sysinfoB

Report this machine's OS, CPU count and RAM. No arguments needed.

Inputs: verbose.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: calc for arithmetic, scribe for video transcription, sysinfo for system information. There is no overlap or ambiguity between them.

    Naming Consistency4/5

    All tool names are lowercase single words (calc, scribe, sysinfo), which is consistent in style. However, they don't follow a strict verb_noun pattern, and one is an abbreviation (calc) while another is a concatenation (sysinfo).

    Tool Count3/5

    Having three tools is borderline appropriate given the server name 'engine' implies a broad utility scope. The count feels thin but not extreme, and each tool seems self-contained.

    Completeness2/5

    The tools cover a calculator, a video transcriber, and system info, which are unrelated domains. There are obvious gaps if this is meant as a general-purpose engine (e.g., no file operations, no networking). The set feels incomplete for any coherent purpose.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A transport-agnostic MCP server that integrates multiple AI coding agents (Claude Code, Gemini, and Codex) with built-in tools for command execution, calculations, and streaming capabilities. Supports both STDIO and HTTP transports for flexible deployment.
      18 npm
      1
      MIT