act101

Analyze. Act. Attest.
Close the loop on quality.

An LLM editing your code is a guess. act101 makes it a transform — your agent does the work, then act gate classifies the change, finds the tests that reach it, diffs the side-effects, and returns a deterministic MERGE / REVIEW / BLOCK verdict with a signed receipt and one-command rollback. 163 grammars, MCP and CLI, one native binary.

New here, and this already reads like gobbledegook? You don't have to understand any of it — your coding agent does.

Show me the plain version →
The closed loop, in full

Three stages. One provable change.

Analyze — 41 analyzers.

dead codecyclescouplinghotspotsseams

map it before you touch it.

Act — 183 refactors.

renameextractinlinemovemodernize

transform it, cross-file, one invocation.

Attest — 6 verify ops + gate.

classifytests reachingside-effectsverdictreceipt

a deterministic verdict, not a rubber stamp.

act gate — deterministic merge gate
$ act refactor extract-variable --file src/cart.ts --start-line 4 --start-column 14 --end-line 4 --end-column 35 lineTotal
{"command":"refactor","operation":"extract_variable","applied":true,"changes_count":2,"files_affected":["src/cart.ts"],"impact_summary":"1 files, 2 locations, 0 references (checkpoint: ckpt-ee03fbe46f88-0000)","_meta":{"timing_ms":444,"output_tokens":52,"naive_tokens":40,"tokens_saved":0,"savings_pct":0.0,"operation_class":"write","deterministic_lines":0,"errors_prevented":0,"session":{"operations":1,"total_tokens_saved":0,"total_deterministic_lines":0,"total_errors_prevented":0,"agent_efficiency_ratio":0.0,"session_duration_ms":444}}}

$ act gate
act gate — working tree vs HEAD (1 changed function(s))
  MERGE   src/cart.ts::computeTotal — format (format-only)
verdict: MERGE
# extract-variable changed the text, not any modeled dimension → clears the gate

$ act history undo
✓ Undid 1 operation(s); restored 1 file(s) on disk

# now the agent makes a change that actually alters behavior…
$ act gate
act gate — working tree vs HEAD (1 changed function(s))
  REVIEW  src/cart.ts::computeTotal — behavior, 3 test(s) reach it (behavior change covered by 3 test(s))
verdict: REVIEW
# behavior changed and tests cover it → routed to you, never auto-merged
act101 online

An AI-Code Health Score for the repos your agent writes.

act101 online is the GitHub-native health scanner for AI-authored code: one grade, two halves — Security and Architecture. It runs in GitHub Actions and lands results where you already work — as a PR comment, a Check Run, and a SARIF upload that opens code-scanning alerts. Free for public repos.

Pricing
Builder Edition
$0
free forever
All queries, 5 codebase analyzers, rename and fix-auto. Personal, non-commercial, and open-source use.
  • 18 query operations
  • 5 codebase analyzers
  • Rename + fix-auto
  • 138 grammars
  • Non-commercial projects
Install Builder Edition
Engineering Edition
$29
billed monthly
Full mutation toolkit for individual commercial development.
  • Everything in Builder
  • Extract, inline, wrap, introduce
  • Generated constructors & accessors
  • Refactor verification & receipts
  • Commercial license
Get Engineering Edition
Elite Edition
$99
billed monthly
Architecture plus the 25 premium languages — COBOL, Fortran, Ada, Verilog, Solidity, and more.
  • Everything in Architecture
  • Legacy: COBOL, Fortran, Ada…
  • Blockchain: Solidity, Vyper…
  • GPU & shaders: CUDA, GLSL, HLSL, WGSL
Get Elite Edition

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

And because act101 answers in one call instead of reading whole files, it runs ~85% leaner on tokens, too.

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 Builder, Engineering, Architecture, and Elite include. Migration and porting are covered separately under Enterprise.

View Feature Matrix →
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. One-command install for Claude Code, Cursor, Codex, Windsurf, Zed, 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

Install it straight from the marketplace, or set it up directly in your tool.

Claude Code
# Register act101 with Claude Code (full plugin: skills + MCP)
$ claude plugin marketplace add act101-ai/act101
$ claude plugin install act101@act101-marketplace
Cursor
# Register act101 with Cursor (writes ~/.cursor/mcp.json)
$ act install cursor
Codex
# Register act101 with Codex (full plugin: skills + MCP)
$ codex plugin marketplace add act101-ai/act101
# Then in any Codex session: /plugins → act101 → Install
Windsurf
# Register act101 with Windsurf (writes ~/.codeium/windsurf/mcp_config.json)
$ act install windsurf
Zed
# Register act101 with Zed (writes context_servers in settings.json)
$ act install zed
opencode
# Register act101 with opencode (writes opencode.json + skills/)
$ act install opencode

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

Who's behind it

Built by an engineer who's spent a career on software that has to be correct

act101 was born out of decades of production experience across financial services, geospatial, automotive, medical devices, and biotech. It's the procedural verification layer built to make coding agents trustworthy: every edit an agent makes is classified, tested against the code that reaches it, and gated before it can merge. Read the story →

Read the story →

Your agent shouldn't ship code without proving it preserves behavior.

Install free.
Run agentic code transformation on your codebase.
Close the loop on quality.

Install free Contact Sales

Free forever for personal use · $29/mo commercial.
Works with every local agentic coding platform.

163 grammars 183 refactoring operations 41 analyzers 18 query operations Agentic code transformation AST-aware refactoring Zero dependencies, zero supply chain risk Instant undo