`pip install vinv`

Vinv runs, tests, and finds issues in your services — with zero code changes.

_{Python services & APIs · runs on your machine · no account, no API keys, no telemetry}

Vinv watches a real run of your Python services and hands your AI coding agent the actual execution evidence — traces, argument values, the failing frame — instead of leaving it to guess from static text. Then it won't let a fix land until it passes acceptance tests written before the fix that the agent never sees.

Your coding agent (Claude Code, Cursor, Copilot…) is the only LLM. No new bill, no provider keys.

Install

pip install vinv

Or run any engine with zero install via uv:

uvx --from vinv exerciser campaign ./my-service --budget 20

_{First run fetches a one-time ~500 MB local embedding model. Python 3.12–3.14.}

Context beats model size

Vinv found four bugs and one performance problem in fastapi/full-stack-fastapi-template (~44k★). Same five issues, same prompts, Vinv grading every run:

Setup	Fixed
Cheap commodity model + Vinv evidence	4 bugs + 1 optimization
Frontier model, working blind	1 bug
Cheap commodity model, working blind	nothing

_{One trial per condition — a demonstration, not a benchmark. The evidence is what
moved, not the weights.}

On the same template the optimization loop detected connection-pool starvation from live traces alone, dispatched the fix, and proved it: sustained-load median 75.6ms → 41.2ms, 45.4% faster (95% CI [36.3%, 45.8%]), responses byte-identical. Upstream on Hugging Face, it found and proved an allocation fast-path in smolagents — ~37,000× less transient allocation, output byte-identical across 2,015 inputs (PR #2572).

What you get — Run · Test · Find · Prove

🏃 Run — brings every service in your repo up under tracing with zero edits to your code: timings, arguments, return values, call trees, from the real run.
🧪 Test — drives real requests through every endpoint (valid, boundary, negative, authenticated) and banks each response as a permanent regression case.
🔎 Find — surfaces what actually broke or slowed down: server errors, crashes, latency hotspots, memory leaks, and dead code — each tied to the exact source line.
✅ Prove — hands that evidence to your coding agent, then verifies its fix against acceptance tests it never sees. A "faster" change that alters any output is auto-reverted.

The engines

pip install vinv installs one package that ships every engine as a console script:

Command	What it does
`exerciser campaign <repo> --budget N`	Start here. One budget across every armed oracle; reports which technique paid
`tracelens run -- <cmd>`	Zero-edit runtime tracing of a Python service or CLI
`identification consolidate <repo>`	Join traces to source; produce the API/call-graph map
`bringup …` · `goal …` · `handbook …`	Service discovery, fix episodes, and the codebase handbook
`vinv-embedder`	The local embedding sidecar (no cloud keys)

Works with any MCP client

Vinv is also an MCP server — point Claude Code, Cursor, or any MCP-compatible agent at it and your agent gets vinv_query (semantic code search), rank_suspects (fault localization over real runs), runtime values_of / slice / coverage_of, and a vinv_session tool that drives the whole verify/optimize loop from chat.

Privacy

100% local. No telemetry, no analytics, no usage pings. Traces stay on your machine and sensitive values are redacted. Apache-2.0.

_{vinv.ai · github.com/VinvAI/VinvAI · Python first — TypeScript & Go next}

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

vinv-0.0.2-py3-none-win_amd64.whl (3.3 MB view details)

Uploaded Aug 21, 2026 Python 3Windows x86-64

vinv-0.0.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.5 MB view details)

Uploaded Aug 21, 2026 Python 3manylinux: glibc 2.17+ x86-64

vinv-0.0.2-py3-none-macosx_11_0_arm64.whl (3.2 MB view details)

Uploaded Aug 21, 2026 Python 3macOS 11.0+ ARM64

File details

Details for the file vinv-0.0.2-py3-none-win_amd64.whl.

File metadata

Download URL: vinv-0.0.2-py3-none-win_amd64.whl
Upload date: Aug 21, 2026
Size: 3.3 MB
Tags: Python 3, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for vinv-0.0.2-py3-none-win_amd64.whl
Algorithm	Hash digest
SHA256	`f4c807c9af5f50c950181c8444116fda5e2cd0de21fa19c907c903a7adf43947`
MD5	`158acfaf817cf076dd29a6311848dfbc`
BLAKE2b-256	`25683db3242d1b40fe1f071ae0e40b0a99f045ad1cec4cccb13c9dd59e285bd6`

See more details on using hashes here.

Provenance

The following attestation bundles were made for vinv-0.0.2-py3-none-win_amd64.whl:

Publisher: publish.yml on VinvAI/VinvAI

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: vinv-0.0.2-py3-none-win_amd64.whl
- Subject digest: f4c807c9af5f50c950181c8444116fda5e2cd0de21fa19c907c903a7adf43947
- Sigstore transparency entry: 2540430990
- Sigstore integration time: Aug 21, 2026
Source repository:
- Permalink: VinvAI/VinvAI@da5b59e9d081637405223996be05cb2387e9cc8c
- Branch / Tag: refs/tags/pypi-v0.0.2
- Owner: https://github.com/VinvAI
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@da5b59e9d081637405223996be05cb2387e9cc8c
- Trigger Event: push

File details

Details for the file vinv-0.0.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: vinv-0.0.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Aug 21, 2026
Size: 3.5 MB
Tags: Python 3, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for vinv-0.0.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`922026e77968513a07d138248eb75c3dee1400b541dff0f31a5e7dfab1654872`
MD5	`b18cd852a6aea0d37de0f1e4498c16ae`
BLAKE2b-256	`8124fd68e6da57f42ff5ebb51d957e326a34f42f8516992a048a24b89d183348`

See more details on using hashes here.

Provenance

The following attestation bundles were made for vinv-0.0.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: publish.yml on VinvAI/VinvAI

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: vinv-0.0.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: 922026e77968513a07d138248eb75c3dee1400b541dff0f31a5e7dfab1654872
- Sigstore transparency entry: 2540431148
- Sigstore integration time: Aug 21, 2026
Source repository:
- Permalink: VinvAI/VinvAI@da5b59e9d081637405223996be05cb2387e9cc8c
- Branch / Tag: refs/tags/pypi-v0.0.2
- Owner: https://github.com/VinvAI
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@da5b59e9d081637405223996be05cb2387e9cc8c
- Trigger Event: push

File details

Details for the file vinv-0.0.2-py3-none-macosx_11_0_arm64.whl.

File metadata

Download URL: vinv-0.0.2-py3-none-macosx_11_0_arm64.whl
Upload date: Aug 21, 2026
Size: 3.2 MB
Tags: Python 3, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for vinv-0.0.2-py3-none-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`e11380efef61635be8499cb3bb20368f231c2da268d4b8743909f0419fbaf481`
MD5	`303f42e1d23e7e411b694544b6357b4b`
BLAKE2b-256	`76026a3d84bd845c974aa80f5a1a3927af6e2efeec706ee673070a4cf27d6127`

See more details on using hashes here.

Provenance

The following attestation bundles were made for vinv-0.0.2-py3-none-macosx_11_0_arm64.whl:

Publisher: publish.yml on VinvAI/VinvAI

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: vinv-0.0.2-py3-none-macosx_11_0_arm64.whl
- Subject digest: e11380efef61635be8499cb3bb20368f231c2da268d4b8743909f0419fbaf481
- Sigstore transparency entry: 2540431060
- Sigstore integration time: Aug 21, 2026
Source repository:
- Permalink: VinvAI/VinvAI@da5b59e9d081637405223996be05cb2387e9cc8c
- Branch / Tag: refs/tags/pypi-v0.0.2
- Owner: https://github.com/VinvAI
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@da5b59e9d081637405223996be05cb2387e9cc8c
- Trigger Event: push

Release history Release notifications | RSS feed

0.0.4

Aug 22, 2026 3 files

0.0.3

Aug 22, 2026 3 files

This release

0.0.2 This release

Aug 21, 2026 3 files

0.0.1

Aug 20, 2026 6 files

0.0.0

Aug 20, 2026 2 files

vinv 0.0.2

`pip install vinv`

Install

Context beats model size

What you get — Run · Test · Find · Prove

The engines

Works with any MCP client

Privacy

Project links

Key dates

1 maintainer

Credits

GitHub Statistics

License

Requires

Tags

Classifiers

Download files

Source Distributions

Built Distributions

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

Release history Release notifications | RSS feed