You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 98d7dba
Browse filesBrowse the repository at this point in the historyBrowse files
feat(ci): add a third release candidate (debug-stripped) as an extra VT draw
Release evidence from run 31744302624 shows the tolerated Microsoft `!ml`
verdict is close to a coin flip per byte image rather than a property of the
code. Across the eight targets the stripped and unstripped candidates of the
SAME linker output disagreed on four, and in both directions:
linux-amd64 stripped microsoft-ml unstripped clean
darwin-arm64 stripped clean unstripped microsoft-ml
linux-arm64 stripped clean unstripped microsoft-ml
If the classifier were keying on something intrinsic to our code the siblings
would agree; they do not. So each variant is close to an independent draw, and
5 of 16 candidates drew the flag.
Two draws is not always enough. On that run linux-amd64-portable came back
microsoft-ml on BOTH candidates, leaving no clean binary to ship for that
target. A third independent draw at a ~31% observed per-candidate hit rate takes
the both/all-flagged case from roughly 1-in-10 per target to roughly 1-in-30.
The third candidate is `--strip-debug` (Apple: `-S`): debug information removed,
symbol table kept. Behaviourally identical to the other two — same linker
output, only metadata differs — but a distinct byte image, which is all
VirusTotal needs to scan it as its own file. Verified on the real v0.10.4
candidates: linux-amd64 gives three distinct hashes (294,634,656 /
294,623,208 / 293,746,096 bytes) and darwin-arm64 likewise, with the ad-hoc
signature verifying after strip.
Selection is unchanged in spirit and now ordered: smallest artifact first
(stripped, debug-stripped, unstripped), take the first CLEAN one, and only if
every candidate drew the tolerated verdict ship the smallest flagged one. A
hard verdict on any candidate still blocks the release before selection.
Cost is 24 objects per release instead of 16.
Derivation enforces that all three hashes differ — identical candidates would be
one draw wearing three hats, and the selector would believe it had alternatives
it does not have. Public claims in README, SECURITY.md and docs/index.html
updated from "both stripped and unstripped" to the three candidates.
All three release contract tests pass, including the native derivation test
which exercises the real strip and codesign path on this host.
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
Copy file name to clipboardExpand all lines: README.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,7 +20,7 @@ High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-si
20
20
21
21
> **Research** — The design and benchmarks behind this project are described in the preprint [*Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP*](https://arxiv.org/abs/2603.27277) (arXiv:2603.27277). Evaluated across 31 real-world repositories: 83% answer quality, 10× fewer tokens, 2.1× fewer tool calls vs. file-by-file exploration.
22
22
23
-
> **Security & Trust** — This tool reads your codebase and writes to your agent configuration files. That is what it is designed to do. If you prefer to audit before running, the [full source is here](https://github.com/DeusData/codebase-memory-mcp). For each release product, both stripped and unstripped executable candidates are submitted to VirusTotal before testing; the selected candidate is then packaged with its SHA-256 unchanged. Release notes link every measured candidate result. Publication permits only the narrowly documented single-Microsoft `!ml` tolerance in [SECURITY.md](SECURITY.md#our-release-policy). All processing happens 100% locally; your code never leaves your machine. Found a security issue? We want to know — see [SECURITY.md](SECURITY.md). Security is Priority #1 for us.
23
+
> **Security & Trust** — This tool reads your codebase and writes to your agent configuration files. That is what it is designed to do. If you prefer to audit before running, the [full source is here](https://github.com/DeusData/codebase-memory-mcp). For each release product, three behaviourally identical executable candidates (unstripped, debug-stripped, stripped) are submitted to VirusTotal before testing; the selected candidate is then packaged with its SHA-256 unchanged. Release notes link every measured candidate result. Publication permits only the narrowly documented single-Microsoft `!ml` tolerance in [SECURITY.md](SECURITY.md#our-release-policy). All processing happens 100% locally; your code never leaves your machine. Found a security issue? We want to know — see [SECURITY.md](SECURITY.md). Security is Priority #1 for us.
24
24
25
25
<palign="center">
26
26
<imgsrc="docs/graph-ui-screenshot.png"alt="Graph visualization UI showing the codebase-memory-mcp knowledge graph"width="800">
Every release is verified through a multi-layer pipeline before publication:
796
796
797
-
-**VirusTotal** — all 16 stripped/unstripped executable candidates across the eight release products are scanned before smoke/soak (clean is preferred and only the single-Microsoft `!ml` tolerance documented in [SECURITY.md](SECURITY.md#our-release-policy) may pass; the number of engines that returned a decisive result is recorded as evidence but is VirusTotal fleet availability, not a pass condition). The selected executable is packaged without changing its SHA-256, and release notes link every candidate result and the selection evidence. Archive containers are checksummed, not redundantly resubmitted.
797
+
-**VirusTotal** — all 24 executable candidates (unstripped, debug-stripped and stripped) across the eight release products are scanned before smoke/soak (clean is preferred and only the single-Microsoft `!ml` tolerance documented in [SECURITY.md](SECURITY.md#our-release-policy) may pass; the number of engines that returned a decisive result is recorded as evidence but is VirusTotal fleet availability, not a pass condition). The selected executable is packaged without changing its SHA-256, and release notes link every candidate result and the selection evidence. Archive containers are checksummed, not redundantly resubmitted.
798
798
-**SLSA Level 3** — cryptographic build provenance generated by the trusted GitHub Actions build workflow; verify with `gh attestation verify <file> --repo DeusData/codebase-memory-mcp --signer-workflow DeusData/codebase-memory-mcp/.github/workflows/_build.yml`
799
799
-**Sigstore cosign** — keyless signatures on all artifacts; bundles included in every release
800
800
-**SHA-256 checksums** — `checksums.txt` published with every release; verified by both install scripts before extraction
Copy file name to clipboardExpand all lines: SECURITY.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -126,7 +126,7 @@ Releases are created as **drafts** (invisible to users) and only published after
126
126
2.**Sigstore cosign signing** — keyless digital signatures verifiable by anyone
127
127
3.**SBOM** — Software Bill of Materials (SPDX) listing all vendored dependencies
128
128
4.**SHA-256 checksums** — published with every release
129
-
5.**VirusTotal scanning** — both stripped and unstripped executable candidates for every release product are scanned before smoke/soak. Zero malicious and zero suspicious is preferred; the only tolerated result is exactly one Microsoft malicious label ending in `!ml`, which is disclosed. The selected executable is packaged without changing its SHA-256; archive containers are checksummed rather than redundantly rescanned. Release notes link every candidate result and the selection evidence.
129
+
5.**VirusTotal scanning** — three behaviourally identical executable candidates — unstripped, debug-stripped and stripped — are derived from one linker output for every release product and scanned before smoke/soak. Zero malicious and zero suspicious is preferred; the only tolerated result is exactly one Microsoft malicious label ending in `!ml`, which is disclosed. The selected executable is packaged without changing its SHA-256; archive containers are checksummed rather than redundantly rescanned. Release notes link every candidate result and the selection evidence.
130
130
6.**OpenSSF Scorecard** — repository security health score
131
131
132
132
Scope of the SLSA claim: this is a build provenance claim for release
Copy file name to clipboardExpand all lines: docs/index.html
+3-3Lines changed: 3 additions & 3 deletions
Original file line number
Diff line number
Diff line change
@@ -165,7 +165,7 @@
165
165
"name": "Does codebase-memory-mcp send my code anywhere?",
166
166
"acceptedAnswer": {
167
167
"@type": "Answer",
168
-
"text": "No. All indexing and querying happen 100% locally on your machine. There is no embedded LLM and no API key — your MCP client acts as the intelligence layer. Before release testing, both stripped and unstripped executable candidates for every platform and link mode are submitted to VirusTotal. The selected candidate is packaged with its SHA-256 unchanged, and release notes link every measured result. Publication permits only the documented single-Microsoft !ml tolerance."
168
+
"text": "No. All indexing and querying happen 100% locally on your machine. There is no embedded LLM and no API key — your MCP client acts as the intelligence layer. Before release testing, three behaviourally identical executable candidates (unstripped, debug-stripped, stripped) for every platform and link mode are submitted to VirusTotal. The selected candidate is packaged with its SHA-256 unchanged, and release notes link every measured result. Publication permits only the documented single-Microsoft !ml tolerance."
0 commit comments