SCIA v4.0 — 7-Stage Intelligence Pipeline

Your AI finally understands
your entire codebase.

AI memory isn't enough. SRT-1 gives you cryptographic provenance over your intellectual contributions. We index your codebase, tag risk, and build a cryptographically signed Trust Chain — proving your team's ownership over everything your AI generates.

pip install srt1-core
Download ZIP
Start Free — No credit card ▶ Watch Demo Read the Docs →
7
Pipeline Stages
10+
Languages
8
Risk Tags
0
Dependencies
See It In Action

Watch SRT-1 index your codebase in real time.

One command. 7 pipeline stages. A signed manifest that proves your AI was working from ground truth.

localhost:7605 — SRT-1 Engine
STAGE 1 — Indexing your codebase
STAGE 2 — Deep code analysis complete
🏷️
SRT1Engine — engine.py:159
Role: ORCHESTRATOR · Risk: AUTH_SENSITIVE, WRITES_TO_DB, FILE_IO
🏷️
SeedTemplateRegistry — seed_templates.py:1
Role: SERVICE_LAYER · Risk: WRITES_TO_DB, HAS_LOGGING
⚠️
Duplicate: _repr()
Found in: authority_client.py:117, seed_graph.py:220, seed_graph.py:263, seed_graph.py:322
📊
166 files · 635 functions · 126 classes · 510 call chains
Languages: Python (77), Markdown (37), HTML (16), JSON (11), TXT (15)
STAGE 3 — Cryptographic trust chain sealed
1
Scan
sha256: a4f2c8…
2
Parse
sha256: 7b91e3…
3
Curate
sha256: d3e0f1…
4
Reflect
sha256: 5c8a2d…
5
Trust
sha256: f9b4e7…
6
Manifest
sha256: 2e6d8a…
7
✓ Verified
Chain intact — 0 tampering
RESULT — Your AI now has full codebase intelligence
166
Files
635
Functions
510
Call Chains
Verified
AGENTS.md — auto-generated
CLAUDE.md — auto-generated
.cursorrules — auto-generated
copilot-instructions.md — auto-generated
srt1_code_manifest.json — signed manifest
Every AI tool now reads the same ground truth. Cursor, Claude, Copilot — all aligned.
Features

Everything your AI needs to know.

One command. One signed manifest. Every AI tool aligned.

🔍

Deep Code Analysis

Parses Python, JavaScript, TypeScript, Go, Rust, Java, C#, and C/C++. Extracts every class, function, and cross-file dependency chain.

🏷️

Role & Risk Tagging

Every symbol gets an architectural role (ORCHESTRATOR, AUTH_SECURITY, SERVICE_LAYER…) and risk tags (AUTH_SENSITIVE, WRITES_TO_DB, DYNAMIC_EXECUTION…).

🔐

Trust Chain

SHA-256 chained hashes across all 7 pipeline stages. Verify the manifest was produced by a clean, uninterrupted run — cryptographically provable.

✍️

Provenance Stamps

Every artifact carries a cryptographic SCIA provenance signature. Detect tampering before trusting any AI output.

Zero Dependencies

Pure Python stdlib. No pip install chain to audit. Ships as a single command: srt1-index --repo_path .

🤖

AI Context Files

Auto-generates CLAUDE.md, .cursorrules, AGENTS.md, and copilot-instructions.md so every AI tool reads the same ground truth.

🌱

Seed Queue

Track every task as a seed through its full lifecycle — planted → germinating → growing → bloomed. Never lose a task mid-session.

🔌

MCP Server

Native Model Context Protocol server for Claude. Every tool call is context-aware, grounded in your actual codebase manifest.

🛡️

Self-Healing Engine

Detects duplicate functions, stale files, and missing docstrings. Auto-proposes governed remediations with full audit trail.

📱

Mobile App (PWA)

Install SRT-1 as a native app on your phone or tablet. Monitor your codebase, check seed status, and review coherence — from anywhere. No app store required.

🖥️

Desktop + Browser

Run the Command Center in your browser or install it as a desktop app. Persistent access to your codebase intelligence without keeping a terminal open.

🏠

100% Local Execution

SRT-1 runs entirely on your own system. No proprietary cloud backends. No VC-funded tracking. The AST indexing and SQLite database live exclusively on your machine.

🔏

Absolute Privacy

Zero IP Leak. Your codebase never leaves your local environment. SRT-1 maps your architecture and protects your intellectual property without ever phoning home.

🔑

Bring Your Own Keys

No middleware API skimming or hidden token taxes. You use your own LLM API keys directly. You control the cost, the context, and the connection.

Language Support

Works with every language your team uses.

Full AST parsing for Python. Regex + structure extraction for everything else.

🐍 Python
🟨 JavaScript
🔷 TypeScript
🐹 Go
🦀 Rust
☕ Java
🔵 C#
⚙️ C / C++
📝 Markdown
🔧 YAML
Pipeline

7 stages. One signed manifest.

1
Scan
Walk directory tree, hash every file
2
Parse
AST + regex across all languages
3
Curate
Detect duplicates & overlaps
4
Reflect
Tag role & risk per symbol
5
Trust
Build SHA-256 chain
6
Manifest
Sign & write JSON
7
Report
Print integrity report
Command Center

Your entire codebase,
live in your browser.

Run the middleware and open localhost:7605/dashboard. The Command Center shows real-time data from your repo — file counts, symbol inventory, seed farm, coherence score — updating as you work.

  • File counts, symbol inventory, cross-file call chains — live from your codebase
  • Seed Farm: every task planted, germinating, growing, and bloomed in one view
  • Coherence gauge: circular drift score that updates every 3 operations
  • Risk profile: auth-sensitive functions, file I/O, dynamic execution — by count
  • Warnings: every duplicate function and curation issue, named and linked
  • "Ask SRT-1" chat: type any question about your codebase, get a grounded answer
localhost:7605/dashboard — SRT-1
49
Files
463
Symbols
226
Call Chains
📊 Coherence
94%
On Track
⚠️ Risk Profile
Auth
78
File I/O
69
Logging
47
🌱 Seed Farm
Add SCIA v4.0 signatures
Wire dashboard route
GitHub Pages deploy
Lemon Squeezy setup
💬 Ask SRT-1
What functions touch auth?_
Mobile PWA — Seed Planting

Plant a seed from your phone.
Your AI builds it.

You're on the train with an idea. Open the PWA, type "add dark mode to the settings page," and plant the seed. SRT-1 generates a full-context blueprint from your codebase — then you review and approve it before anything is dispatched. Once approved, the Execution Bridge sends it to whatever code assistant is already running — Cursor, Claude, Copilot. You check back later: 🌸 BLOOMED — 3 files modified.

Session continuity built in. Every session ends with a handoff summary — what you accomplished, what's pending, and the exact prompt to restart. Close a conversation, come back a week later, paste one line and your AI picks up instantly. No rethinking, no re-explaining.

  • Plant seeds from anywhere — give your code assistant tasks from your phone
  • SRT-1 auto-generates a blueprint using your full codebase context
  • Human-in-the-loop — review the blueprint on your phone, approve or reject before dispatch
  • Execution Bridge dispatches to your assistant via context injection
  • Track lifecycle: 🌱 Planted → 🌿 Germinating → 🌳 Growing → 🌸 Bloomed
  • Session handoff summaries + restart prompts — never re-explain your project
  • Install as a PWA — runs like a native app, no app store required
9:41 📶 🔋
🌱
SRT-1
Seed Farm
✓ PWA
🌱 Plant a Seed
Add dark mode toggle to the settings page with system preference detection
PLANT SEED →
🔍 Review Blueprint
Generated blueprint
Add dark mode toggle to SettingsPage component. Use prefers-color-scheme media query. Store preference in localStorage. Update 2 files.
✓ APPROVE
✕ REJECT
Active Seeds
🌸
Add OAuth2 login
3 files · 12m ago
100%
🌳
Refactor API routes
2 files · building
72%
🌿
Add error boundaries
blueprint ready
25%
🏠
Home
🌱
Seeds
📊
Status
⚙️
Settings
API

Works in 3 lines.

from srt1_code_indexer import SRT1CodeIndexer

indexer = SRT1CodeIndexer(repo_path=".")
manifest = indexer.index_repository()

# Every symbol, tagged and signed
print(manifest["metadata"]["total_symbols_indexed"])  # 661
print(manifest["metadata"]["pipeline_stages"])         # 7
print(manifest["trust_chain"][-1]["stage"])              # "manifest"
Full API Reference → View on GitHub →
Plans

Protect your code. Scale when ready.

The full engine runs free on your machine. Upgrade when you need multi-module orchestration or team sync.

Free
$0
Full single-folder engine. Forever free.
  • Drop-in sandbox — one folder, one engine, one port
  • AST indexing & auto-generated AGENTS.md
  • Live developer dashboard (PWA)
  • File watcher — auto re-index on change
  • Basic enforcement (duplicate detection)
  • Cryptographic trust chain (SeedSignature)
  • Seed lifecycle tracking
  • 100% local — zero network calls
  • Workspace connector (multi-module)
  • Mobile companion
  • MCP Server integration
  • Blueprint generation
  • Team sync
⬇ View on PyPI — pip install srt1-core
Enterprise
$49/seat/month
Team-wide AI governance. Full knowledge infrastructure. Volume pricing available.
  • Everything in Pro
  • Team folder sync — connect developers across machines
  • CTO admin dashboard (God Wheel)
  • Knowledge Graph & semantic retrieval
  • SCIA Memory Orchestrator
  • Recall system — historical context retrieval
  • SSO / SAML authentication
  • Audit trail exports (compliance-ready)
  • SLA support & dedicated onboarding
Contact Sales — Custom Volume Pricing
Original Seed Protection

Your code never leaves your machine.

SRT-1 is built to protect the developer — the Original Seed — and their creations. The engine runs entirely local. Anonymous telemetry is opt-in only, and every payload is logged to your dashboard in real-time. If the engine ever transmits anything beyond what's disclosed, it flags itself as a violation.

✓ Zero outbound calls in Free tier ✓ Source Available — read every line ✓ Self-enforcing transparency ✓ BSL 1.1 Licensed
Also for everyone

Also use SRT-1 to recover your personal AI conversations.

Upload a ChatGPT JSON export. Paste a Claude conversation. Get every abandoned idea back, prioritized and ready to pick up — no setup required.

Try Conversation Recovery →