Air-gapped Dev Copilot

A self-hosted developer assistant for isolated environments.

Industry	Level	Difficulty	Recommended mode
Software engineering	5 of 5	Frontier	hnsw

Coming soon

A complete, runnable Air-gapped Dev Copilot reference implementation is in progress. The architecture and core code below already work with SrvDB 0.3.

The problem

• Regulated teams cannot use cloud copilots.
• Code must not leave.
• Tools must be reviewable.

How SrvDB powers Air-gapped Dev Copilot

1. SrvDB plus local models on internal hardware.
2. Indexes repositories and docs.
3. Reviewable Apache-2.0 component with SBOM.
4. Shared via thread-safe service.

What changes

Today	With Air-gapped Dev Copilot on SrvDB
No AI help	Local AI help
Code leakage risk	Zero egress
Opaque tools	Open source

How it works

1. Deploy local models.
2. Index repos.
3. Serve IDE plugin.
4. Monitor usage.
5. Update models.

SrvDB features it uses

• Fully offline: SrvDB runs in-process and never opens a network connection.
• Thread-safe handles: one database object can be shared between threads; searches run in parallel.
• HNSW graph (hnsw): approximate search that visits a small part of large collections; tune with set_ef_search().
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.

Use cases

• Defence software
• Banking code
• Healthcare systems
• Embedded firmware
• Chip design
• Government IT

Core code

embed() is your embedding model (for example sentence-transformers, or a function that turns your records into feature vectors).

import json
import srvdb

db = srvdb.Database("./air-gapped-dev-copilot-db", dimension=768, mode="hnsw")

def ingest(items):
    """items: list of (id, text, metadata dict)"""
    db.upsert(
        ids=[i for i, _, _ in items],
        embeddings=[embed(t) for _, t, _ in items],
        metadatas=[json.dumps(m) for _, _, m in items],
    )
    db.persist()                      # crash-safe checkpoint

def retrieve_code(query, k=5):
    hits = db.search(embed(query), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Local model quality limits usefulness.

Build roadmap

1. Prototype: load a sample of real data with flat mode and check that searches return what an expert expects.
2. Measure: if you move to an approximate mode, compare its results with flat on the same queries (recall).
3. Pipeline: add continuous upsert and decide when to call persist().
4. Harden: test restarts and crashes, add logging, review every output path with domain experts.
5. Deploy: ship the database directory with the application or service.

All Software engineering projects

Level	Project	What it does
1 · Beginner	Code Search	Find code by what it does.
2 · Intermediate	Codebase Q&A	Ask how the system works and get answers citing files.
3 · Advanced	Bug Dedup Engine	Links duplicate bug reports and similar stack traces.
4 · Expert	Coding Agent Memory	Long-term, crash-safe memory for autonomous coding agents.
5 · Frontier	Air-gapped Dev Copilot (this page)	A self-hosted developer assistant for isolated environments.

See also: Use cases · Live examples (coming soon)