Your Models. Your Workflows. Your Computer.
Build one useful command, connect it to another, and keep the result on your machine. CmdForge makes AI capabilities composable like Unix pipes—and callable from coding agents through MCP.
# Improvise once. Keep what becomes useful.
$ cat meeting.txt | cmdforge run-once \
"Extract decisions and owners from {input}"
# Reusable tomorrow—from your shell or your coding agent:
$ cat meeting.txt | meeting-decisions
Start with a command that solves one problem. Add contracts, composition, and sharing only when the work earns it.
Search local tools and the registry by what they do. For a new idea, forge a personal or project-owned tool from plain language.
Join prompts, Python, CmdForge tools, and MCP calls. Contracts, preflight, regression evidence, and quality coverage keep the result inspectable.
Run tools as ordinary commands, compose them in projects, publish immutable versions, or expose a deliberate allowlist to Codex and Claude Code over MCP.
From natural language query to working solution
# Natural language search:
$ cmdforge registry describe \
"analyze code for security issues"
Matching tools:
official/code-review
Reviews code for bugs, security, and style
rob/security-scan
Focused security vulnerability detection
Semantic search understands intent, not just keywords.
# Tools can call other tools:
steps:
- tool: official/code-review
output_var: review
- tool: rob/summarize
input_template: "{review}"
output_var: summary
# Use like any Unix command:
$ cat app.py | my-review-tool
Build complex solutions from simple, tested components.
Local models, coding CLIs, and OpenAI-compatible APIs—with explicit privacy, capability, fallback, and provenance controls.
No featured tools yet. Be the first to publish!
Learn how to publish a toolInstall curated groups of tools with a single command
Advertisement