Agents that refactor
and port code.

act is the first dev tool that lets an AI agent actually do language-aware code work — agent refactor Python, agent port C to Rust, agent port Ruby to Elixir, agent port COBOL to Java. 163 grammars. 183 AST refactor operations. 30 codebase analyzers. 15 query operations. 8 porting operations. 10 pre-built agent skills. One native Rust binary. Built-in MCP server for Claude Code, Cursor, Codex, and OpenCode. Free for personal use. Your code stays on your machine.

163 grammars in one binary
183 AST refactor operations for AI agents
8 Porting operations for cross-language migration
~85% Fewer tokens than file-based operations (benchmark avg.)
What it does

The first dev tool that lets an AI agent actually refactor and port code.

act is a Model Context Protocol (MCP) server for AI coding agents. It exposes 183 AST-aware refactor operations (extract-function, rename, move-symbol, convert-to-dataclass, extract-trait, inline, and 177 more), 30 codebase analyzers (coupling, cycles, dead code, hotspots, module boundaries, migration readiness), 15 query operations (skeleton, references, callers, graph, control_flow), and 8 porting operations that drive end-to-end language migrations through a contract / inventory / ordering / manifest state machine. Plus 10 pre-built agent skills (architecture-audit, code-review, refactoring, migration-assessment, boundary-analysis, and more) that compose those operations into common engineering workflows. Across 163 grammars.

One native Rust binary. No plugin runtime, no package graph, no supply-chain attack surface.
No indexing, no caching, no cold start — parses on call, results are never stale.
Your code stays on your machine. No telemetry; license verification may contact our servers.
MCP-native. Works with Claude Code, Cursor, Windsurf, or any MCP-aware client.
Agent-executed code work

Agent refactor. Agent port. Agent analyze. Agent migrate.

No tool like this has ever existed. Until act, an AI agent could chat about refactoring but couldn't actually do it — every change was a whole-file rewrite that lost comments, broke formatting, and had no undo. act gives the agent typed, AST-aware operations: extract a function from Python, rename a symbol across a Rust workspace, move a TypeScript module and update every import, port a C library to Rust through a contract / inventory / ordering / manifest state machine. With automatic checkpointing and instant undo on every operation.

Agent refactor

Agent refactor Python, Rust, TypeScript, Go — 163 languages

The agent calls extract-function, rename, move-symbol, inline, convert-to-dataclass, extract-trait, add-type-hints, generate-init, organize-imports, and 174 more — across the entire codebase, AST-aware, with cross-file consistency. Automatic checkpoint on every operation. Instant undo if anything looks wrong.

Agent port

Agent port C to Rust, Ruby to Elixir, COBOL to Java

The agent uses port_contract to anchor the source-to-target migration, port_inventory to enumerate every symbol that must move, port_order to resolve dependency ordering, and a port_manifest state machine (init / add / update / remove / note) to track progress step by step. Works between any two of the 163 supported grammars.

Agent analyze

Agent analyze coupling, cycles, dead code, hotspots, boundaries

30 codebase analyzers: cohesion, coupling, cycles, chokepoints, hotspots, dead code, layers, seams, clusters, surface, fan balance, migration readiness, type completeness, and more. The agent gets a structural map of the repo before it touches a line.

Agent skills

10 pre-built agent skills that compose operations into workflows

architecture-audit, code-review, refactoring, code-navigation, code-generation, migration-assessment, boundary-analysis, change-impact, health-check, architectural-refactoring. Invoke with /skill-name in Claude Code, Cursor, Codex, or OpenCode.

MCP native

Built-in MCP server for Claude Code, Cursor, Codex, OpenCode

One local binary, two transports: act mcp serve for stdio (Claude Code and other MCP clients) and act mcp http for HTTP+SSE (web clients, remote connections). Marketplace install blocks for every major agent host.

Token-efficient

~85% fewer tokens than reading whole files

Query operations return the AST-derived slice the agent needs, not the whole file. references: 99.8% median savings. callers: 99.0%. graph: 95.2%. skeleton: 82.6%. The agent stays inside its context window on real codebases.

The savings

Token-efficient AI code transformation, measured.

We ran act's query and analysis operations against a real monorepo and counted the tokens returned against the tokens an agent would have consumed reading whole files to answer the same question. 166 samples. 10 operations. One headline number.

~85% fewer tokens than file-based operations*
Operation Median savings
references99.8%
callers99.0%
get_type97.7%
mutations95.4%
graph95.2%
skeleton82.6%
interface82.0%
control_flow77.5%
symbols61.5%
repo_outline57.3%

* Unweighted mean of per-operation medians across a 166-sample benchmark on a real-world monorepo, tokenized with o200k_base (act 1.0.3, April 2026). Per-operation medians are reported against the token cost of reading whole files to serve the same query. Actual results will vary with repo size, query target, and language — small repos and short files erode the savings, and in edge cases (e.g. a one-file project where repo_outline is longer than the file itself) can invert them.

Pricing

Start free with agentic refactoring. Scale when you're ready.

Free forever for personal use. See the savings yourself.

Free
$0 forever
 
All queries, 3 analysis tools, rename and fix-auto. Personal, non-commercial, and open-source use.
  • 15 query operations
  • 3 analysis tools
  • Rename + fix-auto
  • 163 grammars
  • MCP server
Install Free
Pro
$19 /mo
$159/year (save 30%)
Full mutation toolkit for individual commercial development.
  • Everything in Free
  • 10 analysis tools
  • Extract, inline, wrap
  • Introduce + generate
  • Commercial license, single dev
Get Pro
Elite
$99 /seat/mo
$899/seat/year (save 24%)
Teams plus the 25 premium languages — Fortran, COBOL, Ada, OCaml, Erlang, and 20 more.
  • Everything in Teams
  • 25 premium languages
Get Elite

All prices USD. 7-day free trial, all features.

Enterprise

Migration and porting. Talk to sales.

C/C++ → Rust. COBOL → Java. Ruby → Elixir. PHP → TypeScript. Python 2 → Python 3. End-to-end migrations aren't a per-seat purchase. Enterprise unlocks the full porting toolkit and the migration analyzers, under an agreement sized to the codebase.

Porting toolkit

8 porting operations — port_contract, port_inventory, port_order, and the port_manifest state machine (init / add / update / remove / note). Drives the migration step by step across any of the 163 grammars.

Migration analyzers

7 analyzers focused on migration readiness, type completeness, surface area, and risk hotspots — so the team knows what's hard before the port begins.

Behavioral equivalence — in development

Differential testing and property-based verification for the source–target pair. Not shipped yet; on the Enterprise roadmap.

Talk to Sales
Get Started

Install act. Give your AI agent real refactoring and porting tools.

One native Rust binary. No dependencies. No supply chain risk. No data exfiltration. Marketplace install for Claude Code, Cursor, Codex, and OpenCode.

macOS / Linux
# Install act101
$ curl -sSL https://raw.githubusercontent.com/act101-ai/act101/main/install.sh | sh
Windows (PowerShell)
# Install act101
PS> irm https://raw.githubusercontent.com/act101-ai/act101/main/install.ps1 | iex

Already have act on your PATH? Register the plugin with Claude Code:

Claude Code
# Register act101 with Claude Code
$ claude plugin marketplace add act101-ai/act101
$ claude plugin install act101@act101-marketplace
Codex
# Register act101 with Codex
$ codex plugin marketplace add act101-ai/act101
# Then in any Codex session: /plugins → act101 → Install
opencode
# Register act101 with opencode (writes opencode.json + skills/)
$ act install opencode

Source, releases, and issue tracker on GitHub: github.com/act101-ai/act101 →

Feature Matrix

What each code intelligence and refactoring license unlocks

Code intelligence, semantic refactoring, architecture analysis, porting, and AI agent skills — broken out by tier so you can see exactly what Free, Pro, Teams, and Elite include. Migration and porting are covered separately under Enterprise.

View Feature Matrix →

Your agents need semantic refactoring.
See it for yourself.

Install free.
Run agentic code transformation on your codebase.
Watch the token count drop.

Install free Talk to sales

Free forever for personal use · $19/mo commercial.
Works with every local agentic coding platform.

160+ grammars 180+ refactoring operations 30 structural analysis operations 15 query operations Agentic code transformation AST-aware refactoring ~85% fewer tokens Zero dependencies, zero supply chain risk Instant undo