updated 2026-10-16 16:07 UTC

Tau

Repository Website by huggingface

A Python port of Pi’s minimalist coding agent.

Coding Agents Python Listed MIT

Is Tau safe? Promising trust profile, but some evidence still deserves review.

OSSF Scorecard 6.8 / 10
Provenance None
Signed commits 84%
Last push 2d ago
Advisories None known
Compare Tau

How does it stack up against its Coding Agents neighbours?

Pick any agent to compare →
Suggest a correction

In detail: Tau scores 71.4/100 (Grade B), ranked #331 of 1378 tracked open-source AI agent projects, on evidence coverage B (3 of 5 independent signal types). The public evidence: no package-provenance attestation found; OSSF Scorecard rates its supply-chain practices 6.8/10; 84% of recent commits are signed; no published advisory affects its latest release (tau-ai); last pushed 2026-10-14. Every point is earned from checkable signals — never paid placement. How scoring works →

How Tau could raise its score

Each line changes one public signal and recomputes with the live scoring function. The gains don't add up exactly, because the score is capped near the top.

Already done? Suggest a correctionAdd the trust badge

Chain of custody

Scanners check what the code says. This traces who ships Tau and whether that has changed: from the source repository, through how changes are reviewed and released, to the package you install. These are the checks for OWASP ASI04 Agentic Supply Chain Vulnerabilities.

  1. Source Signed

    github.com/huggingface/tau, MIT, last pushed 2026-10-14. 84% of the last 100 commits carry a verified signature, so changes trace to a verified account.

  2. Review and release Mixed

    OpenSSF Scorecard rates the repository's practices 6.8/10 (scanned Oct 14, 2026). The checks that decide who can get a change released:

    • Code Review2
    • Branch Protection8
    • Signed Releasesn/a
    • Dangerous Workflow10
    • Token Permissions10
    • Pinned Dependencies7
    All 18 Scorecard checks
    Binary-Artifacts 10
    Branch-Protection 8
    CI-Tests 9
    CII-Best-Practices 0
    Code-Review 2
    Contributors 6
    Dangerous-Workflow 10
    Dependency-Update-Tool 10
    Fuzzing 0
    License 10
    Maintained 10
    Packaging -1
    Pinned-Dependencies 7
    SAST 0
    Security-Policy 0
    Signed-Releases -1
    Token-Permissions 10
    Vulnerabilities 8

  3. Published packages Linked, not attested

    • PyPI tau-ai Source link points back to this repo No build attestation

    Without a build attestation, nothing proves the published files were built from this repository.

  4. What you install today No known advisories

    Latest release checked: tau-ai 0.4.8. No published advisory affects it (OSV, checked 2026-10-16).

Changes to this chain

  • 2026-10-04 OSSF Scorecard: 6.7/10

Evidence behind this score

Coverage B: 3 of 5 independent evidence types found.

  • GitHub repository data
  • Package downloads
  • Supply-chain checks
  • Public actions (missing)
  • Community mentions (missing)

Verify this score yourself

Every build re-issues Tau’s score as an Ed25519-signed credential, valid for 7 days. You can check it offline against HVTracker’s published key; if anyone changes a number after signing, verification fails.

Signed credential (JSON) How to verify

What this score doesn’t check

It covers who ships the code, not what the code does. It doesn’t read tool descriptions or prompts for injected instructions, watch runtime behaviour, or find bugs nobody has disclosed yet. For that, run a content scanner before you connect it, such as Cisco MCP Scanner or Snyk Agent Scan.

How Tau compares in Coding Agents

  1. #13 DeepSeek Harness 72.2 +0.8
  2. #14 Tura 71.6 +0.2
  3. #15 Tau 71.4 this agent
  4. #16 GPTMe 71.0 −0.4
  5. #17 mini-SWE-agent 69.9 −1.5

Bars show each HVTrust score; the tick marks Tau’s 71.4.

Where the 71.4 comes from

HVTrust dimensions vs the Coding Agents average

71.4 / 100 · 100.0% confidence

Tau Coding Agents average (77 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
12.7 / 25
3.5 above avg 9.2
Identity / Provenance60% listing status · 40% build provenance
10.8 / 18
0.9 below avg 11.7
Transparency50% declared license · 50% OSSF Scorecard
14.3 / 17
2.4 above avg 11.9
Maintenance60% last-push freshness · 40% commit activity
17.8 / 20
2.9 above avg 14.9
AdoptionLog-scaled stars · package downloads
12.4 / 20
in line with avg 12.1

Quick Trust Read

What Would Improve It
Publish package provenance or release attestations for stronger supply-chain evidence.
Recent Changes
2026-10-09
Rank Moved
Rank dropped 11 spots (#308 → #319)
2026-10-07
Rank Moved
Rank dropped 22 spots (#283 → #305)
2026-10-06
Rank Moved
Rank rose 12 spots (#295 → #283)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 6.8/10. Tighten the weakest checks to improve public safety evidence.
Publish provenance Add package provenance or release attestations so users can verify where shipped artifacts came from.
Compare with another agent Get email alerts for Tau View Coding Agents Report missing data
76.1
Activity sub-score · out of 100
#15
In Coding Agents

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade B reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage B is separate — it grades how many independent signal types back the score (3 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-10-16 16:07 UTC · Repo last pushed 2 days ago

Rank Trend

2026-09-29 2026-10-16

Activity & Reach

Stars
3.0k
Forks
387
Last Push
2026-10-14
2 days ago
Commits (4 wk)
30
Downloads (7d)
1,043
pypi
HN mentions (30d)
—
Open Issues
58
Rank Change
▼2
was #329

Analysis

Activity Inputs

76.1 / 100
StarsRepository reach
20.8 / 30
FreshnessLast push recency
24.7 / 25
ActivityRecent commits
18.6 / 25
CommunityFork signal
12.0 / 20

Common questions about Tau

Tau has a mixed signal profile. Some trust indicators are present, others are missing. Whether it is safe for your use case depends on which gaps matter to you — review the breakdown below before adopting in production.
Does Tau publish package provenance?
No published build provenance is currently detected for Tau. This is common for open-source projects but means consumers cannot independently verify that the package on the registry matches the GitHub source.
Does Tau have an OpenSSF Scorecard?
Tau has an OpenSSF Scorecard score of 6.8/10. The Scorecard checks for branch protection, signed releases, dependency updates, fuzzing, code review, and other supply-chain hygiene items. See the full check breakdown on this page.
Is Tau actively maintained?
Actively maintained. The repository was pushed to within the last 2 day(s).
What license does Tau use?
Tau ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Tau's commits signed?
84% of the last 100 commits to Tau are verified-signed (GPG, SSH, S/MIME, or GitHub's signing flow). Signed commits help confirm that code was authored by who the commit claims.

Not a safety endorsement. HVTracker describes what public signals show, not whether a project is safe for your use case. Run your own security review before adopting in production.

AI agent surface

MCP, providers, tool surface
Scored in HVTrust

These runtime-trust fields — detected from public repo docs and manifests — contribute a bounded adjustment to this project's HVTrust score alongside supply-chain evidence. The exact values each field can add or subtract are documented in the methodology → Compare this surface across every listed agent in the capability matrix →

MCP Server Support
None detected
No MCP server signal detected.
Detailed evidence is not shown in the public view.
External Service Dependencies
None detected
No clear third-party provider dependency detected.
Credential signal: No explicit API-key/config marker detected.
Tool / Plugin Surface
medium confidence
Extensions
Extension based plugin/integration surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
high confidence
Match
Published package metadata matches the tracked repo
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live

Maintain Tau?

For maintainers

HVTrust scores Tau from public signals only — we never contact maintainers first. If a signal is wrong, stale, or missing (provenance you publish, a Scorecard you run, signed releases), tell us and we'll review it. Corrections are public and tracked on GitHub.

Submit a correction → Add the trust badge

Reputation Timeline

Signal history
Rank 4Listed 1HVTrust 1Grade 1Scorecard 1
2026-10-09
Rank Moved
Rank dropped 11 spots (#308 → #319)
2026-10-07
Rank Moved
Rank dropped 22 spots (#283 → #305)
2026-10-06
Rank Moved
Rank rose 12 spots (#295 → #283)
2026-10-04
Scorecard Added
OSSF Scorecard: 6.7/10
2026-10-04
Grade Changed
Trust grade D → B
2026-10-04
Rank Moved
Rank rose 881 spots (#1177 → #296)
2026-10-04
HVTrust Changed
HVTrust up 32.1pts (39.9 → 72.0)
2026-09-29
Newly Listed
First tracked at rank #1179
GitHub → Website → PyPI: tau-ai

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 71.4 Grade B
Markdown:
[![HVTrust](https://hvtracker.net/badge/tau.svg)](https://hvtracker.net/agents/tau)
HTML:
<a href="https://hvtracker.net/agents/tau"><img src="https://hvtracker.net/badge/tau.svg" alt="HVTrust"></a>

Other agents in Coding Agents

Data sources
GitHub REST API (repo, commits, stars, forks, license) · PyPI / pypistats (downloads, provenance) · OpenSSF Scorecard CLI
Each agent's signals refresh once daily across 6 staggered batches. Methodology v4.4 · Raw JSON