Hybrid retrieval
Each query combines semantic search and exact keyword matching, then fuses the rankings so the strongest results rise to the top.
Private code memory for AI
Give your AI grounded answers over private repositories, without uploading source code.
SourceVault indexes your repositories and their entire git history on hardware you already own (a laptop, a workstation, a server in your rack) and answers questions about the code, including why it changed, with file-and-line citations. Nothing is sent to a third party.
What buyers get
- A dashboard with cited answers, a full source viewer, watches, and runbook export.
- Hermes plugin plus an MCP server for any MCP client.
- Git-history answers, module overviews, and AI-change provenance, none of which a cloud indexer can see.
- A 7-day free trial of the full product on one source. No account or card required.
- Sentinel trust layer: an access policy over what AI can read, secrets redacted from every answer, and a tamper-evident audit log.
- One-command install on macOS, Linux, and Windows, with GitHub, GitLab, and Bitbucket supported.
The problem
Hosted AI tools break down when the code is private.
Most code assistants want to upload your repository, keep it in a cloud context window, and answer from a lossy slice of your system. That creates privacy risk, compliance concerns, and weak answers when the repo is large or sensitive.
SourceVault is built for teams that need private code intelligence on local infrastructure.
The engine
Local index, exact reads, grounded answers.
The engine implements the retrieval patterns the major RAG frameworks document as best practice, built directly on ChromaDB and Ollama, with an optional Qdrant engine that SourceVault runs for you when full git history takes a repository to serious scale. The stack stays small enough to audit line by line.
Code-aware chunking
Files are split along function and class boundaries, so every result maps to readable code with exact line ranges.
Context-aware embeddings
Each chunk is embedded with its path and symbol names, so the vector store knows where each piece of code lives in the repository as well as what it says.
Grounded answers
Ask mode checks whether it has enough context, retrieves again if needed, and answers only from source-backed snippets instead of guessing.
Cost model
Retrieval is cheaper than re-reading the repo.
An AI agent will re-read a whole file to find one function, then drag that stale context forward turn after turn. The waste compounds with every question a developer asks, and per-seat plans meter all of it. SourceVault answers from a bounded budget of cited file and line ranges instead. Repeated questions return from cache without a model call, and local models have no meter at all.
Per-seat feesNone. Runs for the whole team on one machine you control
Per-token billingNone for local answers; repeated questions return from cache with zero model calls
Context per answerA bounded budget (about 6k tokens by default) of cited file and line ranges
Source code egressNone. Nothing is uploaded, logged, or retained by a third party
Why SourceVault
What you get beyond code search.
The engine tracks how your code connects, re-checks its answers as the code changes, and controls what AI tools are allowed to read. All of it is driven from a browser dashboard the whole team can use. A few highlights:
100% local by design
Embeddings run on local Ollama, vectors live in local ChromaDB, and answers come from local models.
SourceVault Sentinel
An enforcement layer between the index and everything that reads it. An access policy gates which files can be read at all, a DLP pass redacts secrets from every answer before delivery, and each decision lands in a tamper-evident, hash-chained audit log.
Git history answers
Commit messages are indexed alongside code, so questions like "why was this changed?" and "when did this break?" are answered from the actual commits. Cloud indexers can't do this, since they only ever see a snapshot of the tree.
Multi-repo AskPro
Ask one question across every indexed repository at once, with each citation tagged by repo. "How do the frontend and backend handle this?" comes back as a single answer. Standard from Pro up.
Watches
Pin a question as a standing check. After every reindex it runs again and flags you if the cited answer has drifted. Useful for questions like "did the auth flow change this sprint?"
Works with your AI tools
An MCP server exposes the same engine to OpenClaw and any other MCP client, which get bounded, cited context instead of re-reading files. The server itself is local-only. Pair it with a local-model client and the whole loop runs offline; a cloud-backed client sends what it retrieves to its own vendor, by your choice.
Pricing
Free for 7 days, then a one-time payment.
Pricing scales with the number of sources you index, where a source is a repository or a local folder. There are no per-seat or per-token fees, and loose files you add individually share a single source slot. A license is a one-time payment with 12 months of updates included; the version you installed keeps working after that, and renewing updates later costs a fraction of list price. Priority Support is an optional subscription for teams that want an SLA and hands-on tuning.
Start with the free trial
One command installs the full product with one source for 7 days. No account, no card. If it can't answer questions about your code with file-and-line citations, don't buy it.
Starter
$1,350 one-time
30 days of Priority Support included
For a founder or solo engineer who needs private code memory without a heavy platform project.
- One-command install (macOS, Linux, Windows/WSL2)
- Up to 3 indexed sources (repos or local folders)
- Dashboard, Hermes plugin, MCP server
- Git-history answers and module overviews
- Yours forever · 12 months of updates included
- License key by email, activates instantly
Pro
$3,800 one-time
30 days of Priority Support included
For a power user or small team running AI across several private repos.
- Multi-repo Ask included
- Up to 15 indexed sources (repos or local folders)
- Everything in Starter
- Webhook-driven reindex on every push
- Watches: standing questions that re-check themselves
- Yours forever · 12 months of updates included
- License key by email, activates instantly
Team
From $8,200 one-time
30 days of Priority Support included
For an engineering team or large monorepo that needs a deliberate rollout.
- Multi-repo Ask included
- Up to 4 machines, shared team setup
- 15+ sources or a large monorepo, with no source cap
- Security-focused file exclusions
- Team onboarding and maintenance runbook
Enterprise
Custom
Priority Support SLA
For regulated or air-gapped environments that need the compliance story in writing.
- Multi-repo Ask included
- Unlimited sources
- Air-gapped install: offline bundle and models
- Signed compliance reporting over the Sentinel audit chain
- Compliance pack with zero-egress verification
- Multi-machine rollout, scoped to your environment
Add-ons
Priority Support Subscription
A support SLA plus hands-on help: model and resource tuning for your hardware, and reindex strategy when embedding models change. Flat $195/mo for any plan, after the 30 days included with every license. Requires an active SourceVault license (buy with the same email). Cancel anytime.
Updates renewal Existing customers
Your license and installed version work forever. When your 12-month updates window ends, renew to keep receiving new releases: Starter $550, Pro $1,550, one-time. The fresh key arrives by email and replaces the old one in the dashboard's License settings.
A "From" price is a floor, and your quote is fixed before work starts. Send your stack, repo count, and target machine and you will get a straight recommendation, even if the right answer is the smaller package.
Every license carries a 14-day money-back guarantee, and nothing ever auto-renews; the details are in the billing & refund policy. Starting small is safe, too. Starter customers can upgrade to Pro any time for the difference in list prices ($2,450 today). The upgrade option appears in your dashboard's Settings once you're licensed, or email support.
Deployment
One command on every platform.
The models, the index, and the dashboard all run on machines you control. One command installs everything on macOS, Linux, or Windows (WSL2), or use the shared Docker Compose deploy where teammates on any OS connect through the browser. Every install includes the 7-day free trial.
Questions?
Talk to a human before you buy.
Team and Enterprise rollouts, air-gapped installs, checkout trouble, or anything the trial can't settle: email us and you'll get a straight recommendation, usually the same day. For install help, Discord is fastest.