Spaghetti is Toast.
The architecture enforcement engine for AI-generated code.
Live numbers — every badge below reads from forge.atomadic.tech/metrics.json on each render.
AI agents write code 10x faster than humans can review it. Pattern violations went from 5% to 60% post-LLM. Your codebase is accumulating architectural debt at machine speed.
Forge fixes that.
🎯 300+ public OSS Python repositories absorbed end-to-end. fastapi (98k★), scrapy (61k★), django-rest-framework (30k★), pytest (13.8k★), langgraph (31k★), openai-agents-python (26k★), cookiecutter (25k★), aiohttp (16k★), deepeval (15k★), DocsGPT (17k★), txtai (12k★), E2B (12k★), copier, apscheduler, msgspec, peewee, alembic, tortoise-orm, presidio, dagster, IBM mcp-context-forge, and ~290 more — every single one ran through one
forge autocommand, emerged 5-tier-organized, wire-clean, scaffold-complete, deterministic. Wire-PASS holds across the entire 300-seed corpus. Receipts inHARVEST_LEDGER.md.
- Catches architectural violations AI agents leave behind. Deterministic tier-law enforcement — no LLM in the loop, no hallucinations. Four monadic laws (MCB, AIOM, AHLP, IFWC) shipped as advisory AST scanners; promote to
--fail-on-violationswhen ready. - Verifiable token savings. Every Forge verb auto-appends to a file-backed JSONL ledger at
<project>/.atomadic-forge/lifetime_savings.jsonl.forge token-savingsprints the running total and per-tool breakdown. Auditable line-by-line — not a marketing claim. - Surgical capability grafting.
forge graft --source-file X --symbol Yextracts a single function or class from any Python source, lands it in the right tier, and auto-wires CLI + MCP. Sibling references resolve automatically. Closes the gap between whole-repotransmute autoand one-shot surgical absorption. - Deterministic recipe replay.
forge replay <recipe>runs a golden command chain (release hardening, add-cli-command, fix-wire-violation, add-feature, publish-mcp) as subprocesses — zero LLM round-trips per step. - One command: spaghetti -> certified architecture. Python, JavaScript, TypeScript, Rust, Go, Swift, Kotlin — full pipeline (recon, wire, certify, scaffold, evolve) on every language. Recon cache short-circuits the AST walk on unchanged trees via tree fingerprint.
- Bring your own LLM. Built-in presets for OpenAI, Anthropic, Gemini, OpenRouter, DeepSeek, Groq, Together, Fireworks, xAI, Mistral, Perplexity, Cerebras, Hyperbolic, AAAA-Nexus, and Ollama — plus
forge config provider addfor any custom OpenAI-compatible endpoint. See docs/PROVIDERS.md. - IDE-native. VS Code extension (
vscode-extension/), MCP server for Claude Code / Cursor / Cowork / Windsurf, four ready-to-use Claude Code skills. See docs/IDE_INTEGRATION.md.
Forge is an architecture enforcement engine, not a linter. It imposes deterministic structure on AI-generated code — and it ships proof that the structure holds.
-
Architectural drift stops here.
forge autoruns recon, detects every upward-import violation, re-tiers mislaid files, and emits a signed conformance receipt — all in one command. Validated against 300+ OSS repositories: Wire-PASS holds across the entire corpus. -
Context overhead you can actually measure.
forge context_packpre-bundles repo context into a single optimized payload for AI agents, cutting redundant re-reads. Every Forge verb logs its savings to a file-backed JSONL ledger at<project>/.atomadic-forge/lifetime_savings.jsonl— runforge token-savingsto see the auditable running total, line by line. -
Composition opportunities no human would find.
forge emergent scanperforms cross-repo AST analysis to surface capability combinations that exist in your codebase but have never been wired together. Discovery is deterministic — no LLM guessing, no hallucination false positives. -
One command: spaghetti to certified.
forge autotakes any Python, JS, TS, Rust, Go, Swift, or Kotlin repo from chaos to 5-tier-organized, 0 wire violations, 100/100 certify score. The before/after is not a demo — receipts are inHARVEST_LEDGER.md. -
Bring your own LLM — any of them. OpenAI, Anthropic, Gemini, OpenRouter, Ollama, DeepSeek, Groq, Mistral, and 10+ more ship as built-in presets. Add any OpenAI-compatible endpoint with
forge config provider add. No vendor lock-in, no rewiring required. -
Enforcement that scales with AI output velocity. Forge's tier-law scanner is pure AST — no LLM in the loop, no nondeterminism. Promote violations from advisory to
--fail-on-violationsand it becomes a hard CI gate. Architecture holds at the speed AI generates code.
pip install atomadic-forge # install
forge recon . # scan any repo (free, read-only)
forge certify . --print-card # get your architecture score (0-100)That's it. No API key, no config, no writes.
Forge enforces a 5-tier monadic law — every source file belongs to exactly one tier, tiers compose upward only. AI agents generate code fast; Forge gives it gravity.
a4_orchestration/ <- CLI, entry points
|
a3_features/ <- Feature modules
|
a2_composites/ <- Stateful classes
|
a1_functions/ <- Pure functions
|
a0_constants/ <- Constants, enums (zero logic)
Before Forge:
62 import violations · certify score 23/100 · "it works on my machine"
After forge auto:
0 violations · certify 100/100 · signed conformance receipt · ship it
| Command | What it does |
|---|---|
forge auto |
Flagship. recon → cherry → wire → certify → receipt |
forge recon |
Scan a repo — classify every symbol, show tier distribution |
forge wire |
Detect upward-import violations |
forge certify |
Architecture score (0-100): docs, tests, tier layout, imports |
forge verify |
Composite ship gate: PASS / REFINE / FAIL |
forge enforce |
Apply mechanical fixes (rollback-safe) |
forge status |
Wire + certify in one call |
forge welcome |
First-call handshake — score + guidance in one response |
| Command | What it does |
|---|---|
forge smell |
Code smell scan: cyclomatic complexity, long functions, duplicates |
forge call-graph |
AST call graph for any symbol |
forge call-graph-summary |
Whole-package call-graph portfolio — orphans, fan-in hotspots, max depth |
forge churn |
File-level git commit frequency — hotspot and stable files |
forge cna-check |
Compose-Not-Add — flag duplicates before writing |
forge trust-gate |
LLM response hallucination detector |
forge preflight |
Pre-edit guardrail: tier + import + scope check |
forge surface-gaps |
Find a1 entry points missing MCP or CLI coverage |
forge wire-stubs <module> <function> |
Generate MCP handler + CLI stub + test skeleton for any unwired a1 function |
forge capability-scout --queries "q1,q2" |
Search GitHub for harvest target repos |
forge dead-code |
AST-walk dead symbol detector (vulture synthesis) |
forge maintainability |
Maintainability Index per module (radon MI: A/B/C/D ranking) |
forge concept-bridge --harvest-json path/to/harvest.json |
Convert harvest candidates below TAU_TRUST into actionable synthesis plans |
forge token-savings |
Lifetime token-savings total + per-tool breakdown from .atomadic-forge/lifetime_savings.jsonl |
forge replay <recipe> |
Run a golden recipe's validation gate as subprocesses — zero LLM round-trips; flags: --dry-run, --keep-going, --list, --json |
| Command | What it does |
|---|---|
forge mcb-check |
Flag unbounded while loops and recursion in tier-a1 atoms (Monadic Compute Bounding) |
forge aiom-check |
Flag forbidden I/O imports (requests, urllib, socket, subprocess) in tier-a1 (Algebraic I/O Monad) |
forge fingerprint |
SHA-256 of every a1 module's normalised AST — tamper-evident, stable across whitespace (AHLP) |
forge fuzz <module> |
Hypothesis property tests on any a1 callable carrying __invariants__ (IFWC-lite) |
| Command | What it does |
|---|---|
forge create |
Intent + seed repos -> new pip-installable package |
forge emergent scan |
Cross-domain composition discovery |
forge recon-swarm |
Walk N repos, unified report |
forge harvest |
Cross-repo capability gap finder |
forge graft --source-file <f> --symbol <name> |
Extract one function/class from any Python source and land it in the target's correct tier; --rename for private→public; auto-wires CLI + MCP |
| Command | What it does |
|---|---|
forge iterate |
LLM loop: intent -> code -> absorb -> score -> iterate |
forge evolve |
Recursive improvement over N rounds |
forge plan |
Bounded execution plan with risk + rollback |
forge chat |
Terminal copilot over forge docs |
84 CLI verbs total. Full reference: docs/02-commands.md
Forge ships a Model Context Protocol server. Add it to Cursor, Claude Code, Aider, Devin, or any MCP-compatible agent:
{
"mcpServers": {
"atomadic-forge": {
"command": "forge",
"args": ["mcp", "serve", "--project", "/path/to/your/repo"]
}
}
}11 tools, 92 actions locally. All legacy tool names redirect automatically — existing callers keep working. Deployed Worker at forge.atomadic.tech/mcp. Listed in the MCP Official Registry.
| Tool | Actions | What it does |
|---|---|---|
welcome |
— | RECOMMENDED FIRST CALL: onboarding scan, score, narrative, capability tour |
explore |
17 | Analyze, understand, discover — recon/explain/call_graph/call_graph_summary/smell/lineage/harvest/synergy/scan/swarm/churn/surface_gaps/capability_scout/dead_code/maintainability/concept_bridge |
audit |
23 | Quality gates, change safety, trust |
plan |
10 | Orient + dev utilities — context/compose/policy/recipes/generate/apply/locate/commit/scaffold/steersman |
transmute |
3 | FLAGSHIP spaghetti→certified pipeline — auto/cherry/finalize |
loop |
4 | LLM iteration loops — iterate/resume/evolve/evolve_step |
hive |
13 | Multi-agent coordination — lifecycle, consensus, handoffs, enhancements |
wisdom |
5 | Institutional memory DB — record/query/list/recall/promote |
nexus |
7 | AAAA-Nexus auth primitives (uses op= not action=) — identity/federation/authorize/trust/contract/lineage/ratchet |
inspect |
10 | Low-level AST inspection — body/symbol/class_signals/ast_scope_blueprint/mint_ast_locks/add_node/classify_repo_layout/fingerprint_repo/synthesis_plan/swarm_repo_specs |
create |
— | Intent + seed repos → shippable pip package (Phase 1 pipeline: emergent_swarm + materialize) |
Note:
nexususesop=as its dispatch key instead ofaction=to avoid collision with theauthorize_actionoperation's ownactionparameter that passes through to the Nexus API.
Full tool reference: docs/MCP_TOOLS.md | First call: welcome
Every number below is a live read from
forge_metrics.json— the canonical metrics artifact regenerated on every push byforge metrics --apply. CI fails any PR that lets the file drift.
| Metric | Value |
|---|
| MCP tools | 11 tools · 92 actions | | CLI verbs | 84 | | Source files | 247 (~49K LOC) | | Tests | 1635 passing across 123 test files | | Lean4 formal proofs | 872 theorems (mathematically verified core logic) | | Monadic tiers | 5 (a0 → a4, strict upward-only composition) | | Languages | Python, JS/TS, Swift, Kotlin, Go, Rust | | Infrastructure cost | $5/mo | | Self-score | 100/100 certify · 0 wire violations | | License | BSL 1.1 (Apache 2.0 after 2030-04-27) |
Forge eats its own cooking. Every CI run scores itself.
Production-tested at scale. 300+ public Python repos absorbed end-to-end via
forge auto— fastapi (98k★), scrapy (61k★), pytest (13.8k★), DRF (30k★), cookiecutter (25k★), and ~295 others. Wire-PASS on every single one. Full receipt:HARVEST_LEDGER.md.
| Tier | Price | What you get |
|---|---|---|
| Free | $0 | OSS, 25 calls/day, read-only tools |
| One-Time Refactor | We run auto on your repo -> PR targeting 100/100. One revision included. |
|
| Starter | $79/mo | All 11 tools (92 actions), 5k calls/mo, signed receipts, custom recipes |
| Pro | $249/mo | + notarization, compliance attestations, cross-repo telemetry |
| Founding Member | $999/yr | Everything. Forever. First 25 only. |
| Enterprise | Custom | BSL commercial license, SSO, self-host, SLA |
Launch special: The one-time refactor is $99 (normally $149). See what Forge does to your codebase before committing to a subscription.
| First 10 Minutes | Install, demo, first scan |
| Tutorials | Quickstart, 5-tier law, LLM integration |
| Architecture | How Forge itself is built |
| CI/CD Integration | GitHub Actions, GitLab CI, pre-commit |
| Showcase | Live run trajectories |
| Changelog | Version history |
| Contributing | How to extend Forge |
| Security | Vulnerability reporting |
Business Source License 1.1. Free for non-production use. Commercial license for production — see COMMERCIAL_LICENSE.md. Change Date: 2030-04-27 -> Apache 2.0.
forge.atomadic.tech — paste any GitHub repo, watch the analysis in real time.
Interested in investing?
