act101 logo

act101

For AI agents: act101 enables code navigation, refactoring, and analysis across 163 programming languages via MCP integration.

Built by Kage Martin · Artificial Intelligence · Developer Tools · Freemium

Visit website

In category: #693 of 2052 · Artificial Intelligence

act101 is a Community listing on Launch Llama with 35 total upvotes, founded by Kage Martin who joined in May 2026, compared against 6 alternatives.

Community listing

Listing status

35upvotes

Community score

Kage Martin (Joined May 2026)

Founder

Launched on Launch Llama May 13, 2026 · #10 of 54 that day

act101

About

codebase navigation, semantic refactoring, structural analysis, and language migration supportive 163 grammars in one native binary

Follow act101: X (Twitter) · LinkedIn

Use Cases

  • Verifying each refactor an AI agent makes to a codebase before it merges, with a MERGE, REVIEW, or BLOCK verdict
  • Performing deterministic cross-file refactors such as rename, extract, inline, and move instead of whole-file LLM rewrites
  • Rolling back agent-made changes with one command using signed receipts when a change breaks something

Who it is for

  • Individual engineers who want to verify every refactor their AI agent makes before it merges.
  • Codebase owners and architects who need to track structural drift and prove refactors on every commit.
  • Open-source maintainers running an AI agent on open-source or non-commercial repositories.

Pricing

Install is free and Builder is free forever for open-source and non-commercial work.

View act101 pricing →

FAQ

Can an AI agent actually refactor my Python codebase with act?

Yes. act ships as one native binary with two interfaces — MCP and a CLI — both exposing the same 182 AST-aware refactor operations, so agents like Claude Code, Cursor, Codex, and OpenCode can call rename, extract function, inline, move symbol, convert-to-dataclass, add-type-hints, and 60+ Python-specific refactors directly, with cross-file import updates, automatic checkpoint, and instant undo.

Can an AI agent port a C codebase to Rust?

Yes. act provides 10 porting operations — port_contract, port_inventory, port_order, a port_manifest state machine, and cross-language adapter/shim generators — that let an agent define a source-to-target contract, inventory every symbol that must move, resolve dependency ordering, and track the migration step by step. The same workflow handles Ruby to Elixir, COBOL to Java, Python 2 to Python 3, and arbitrary source-to-target language pairs across 163 supported grammars.

How is act different from ast-grep, comby, or semgrep?

ast-grep, comby, and semgrep are pattern-matching and structural search tools designed for humans. act is one native binary that exposes typed, parameterised refactor operations (extract-function, rename, move-symbol, etc.) through MCP and a CLI, with automatic checkpointing and instant undo. It lets an agent perform end-to-end refactoring and cross-language porting without rewriting whole files.

Which AI coding agents work with act?

act is one native binary that is both an MCP server and a CLI. Run act mcp serve and Claude Code, Cursor, OpenAI Codex, and OpenCode connect via stdio or HTTP+SSE — or run any act subcommand directly. Marketplace install blocks are included for the agents above.

How real is the ~88% token saving?

It is measured, not estimated: ~88% fewer tokens on query operations — skeleton, references, callers — versus reading whole files, from timed runs against real repositories. The method and raw numbers are published at act101.ai/benchmarks and act101.ai/methodology. It applies to reads, not writes, and it is a side effect of answering from the AST instead of shipping whole file contents; the product's job is the verdict and the receipt.

Is cross-language porting production-ready?

Porting is a workflow, not a button. act ships 10 porting operations — contract, inventory, dependency ordering, a manifest state machine, and adapter/shim generators — plus parity verification that checks a ported function behaves like the original. The agent does the work; act makes each step checkable and keeps score in the manifest. Small, well-tested modules port well today. A large legacy migration is a program of work run step by step under the manifest — that is what the Enterprise engagement covers. Evaluate the claim by porting one module and reading the parity report.

Why not just have the LLM review the diff?

An LLM review is a second opinion from the same kind of process that made the mistake — probabilistic, prompt-sensitive, different answer on a rerun. act101's gate is a different kind of process: it classifies the change against the code's structure and the tests that actually reach it, and returns the same verdict for the same input, every time, with a receipt you can replay. Opinions are useful. Merges need verdicts.

Isn't CI enough?

Tests check the behavior someone intended to check. Agentic debt is what accrues in the changes nobody intended: structure drift, silent behavior shifts, coupling nobody designed. act gate classifies every changed function — format-only, behavior change covered by tests, behavior change uncovered — so the uncovered ones route to you instead of merging quietly. CI stays; the gate is the layer CI was never built to be.

Alternatives

DevlawsFor engineering teams: DevLaws enforces coding standards inside AI agents via MCP, ensuring compliant code before it's written.ArachneFor AI teams: Arachne converts websites into structured Shadow APIs for agents, replacing brittle scraping with governed, auditable interfaces.MetaFor developers: Meta's Muse Code terminal agent executes repository-scale coding tasks with persistent background agents so you ship faster.AgentsKitFor developers: AgentsKit provides open-source TypeScript components for building AI agents so you avoid vendor lock-in and swap layers freely.CodeHealth MCP Server by CodeSceneFor AI coding teams: CodeHealth MCP Server guides agents to write maintainable, production-ready code by catching risks and preventing technical debt in real-time.The Agentic Coding KitFor developers: The Agentic Coding Kit provides 34 preset files, subagents, and git hooks so Claude and Cursor follow your project conventions instead of ignoring them.

More in Artificial Intelligence

All Artificial Intelligence tools

New on Launch Llama

Launched this week · This month's launches · All products A–Z

Tags

#code navigation#semantic refactoring#structural analysis#language migration#mcp integration#multi-language support#ai coding agents#native binary

Ask AI about act101

ChatGPT Claude Perplexity Grok

Supporters

2 founders

2 founders supported act101 on Launch Llama.

Kage Martin

For bots & AI agents

Machine-readable versions of act101 and Launch Llama. Fetch these instead of parsing this page.

This listing (.md) llms.txt llms-full.txt ai.txt Full catalog (.md) Endpoint index API docs MCP server MCP manifest Developer docs