updated 2026-10-31 08:12 UTC

Hindsight

Repository Website

Hindsight: Agent Memory That Learns

Memory & Knowledge Python Listed MIT

Is Hindsight safe? Strong public trust posture, backed by multiple independent signals.

OSSF Scorecard 4.9 / 10
Provenance Attested
Signed commits 97%
Last push today
Compare Hindsight

How does it stack up against its Memory & Knowledge neighbours?

Pick any agent to compare →
Suggest a correction

In detail: Hindsight scores 86.5/100 (Grade A), ranked #80 of 1374 tracked open-source AI agent projects, on evidence coverage A (4 of 5 independent signal types). The public evidence: its packages ship with cryptographic provenance; OSSF Scorecard rates its supply-chain practices 4.9/10; 97% of recent commits are signed; last pushed 2026-10-31. Every point is earned from checkable signals — never paid placement. How scoring works →

How Hindsight 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 Hindsight 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/vectorize-io/hindsight, MIT, last pushed 2026-10-31. 97% 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 4.9/10 (scanned Oct 26, 2026). The checks that decide who can get a change released:

    • Code Review0
    • Branch Protection3
    • Signed Releases0
    • Dangerous Workflow10
    • Token Permissions0
    • Pinned Dependencies1
    All 18 Scorecard checks
    Binary-Artifacts 9
    Branch-Protection 3
    CI-Tests 9
    CII-Best-Practices 0
    Code-Review 0
    Contributors 10
    Dangerous-Workflow 10
    Dependency-Update-Tool 10
    Fuzzing 0
    License 10
    Maintained 10
    Packaging 10
    Pinned-Dependencies 1
    SAST 0
    Security-Policy 10
    Signed-Releases 0
    Token-Permissions 0
    Vulnerabilities 0

  3. Published packages Partly attested

Changes to this chain

No change to package provenance, package source links, Scorecard coverage or license in HVTracker's daily snapshots of Hindsight.

Evidence behind this score

Coverage A: 4 of 5 independent evidence types found.

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

Verify this score yourself

Every build re-issues Hindsight’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 Hindsight compares in Memory & Knowledge

  1. #5 OpenViking 87.6 +1.1
  2. #6 Graphiti 86.5 ±0
  3. #7 Hindsight 86.5 this agent
  4. #8 Cognee 86.1 −0.4
  5. #9 Vespa 84.1 −2.4

Bars show each HVTrust score; the tick marks Hindsight’s 86.5.

Where the 86.5 comes from

HVTrust dimensions vs the Memory & Knowledge average

86.5 / 100 · 100.0% confidence

Hindsight Memory & Knowledge average (50 agents)

Safety / Integrity50% OSSF Scorecard · 30% provenance · 20% signed commits
18.5 / 25
6.6 above avg 11.9
Identity / Provenance60% listing status · 40% build provenance
18.0 / 18
5.3 above avg 12.7
Transparency50% declared license · 50% OSSF Scorecard
12.7 / 17
in line with avg 13.0
Maintenance60% last-push freshness · 40% commit activity
20.0 / 20
2.8 above avg 17.2
AdoptionLog-scaled stars · package downloads
17.2 / 20
4.1 above avg 13.1

Quick Trust Read

What Would Improve It
Improve safety / integrity to lift the weakest part of the trust profile.
Recent Changes
2026-10-23
Provider Removed
Runtime surface shrank — no longer detected: Anthropic
2026-10-13
Rank Moved
Rank dropped 14 spots (#81 → #95)
Maintainer Checklist
Raise Scorecard signals Current OSSF Scorecard is 4.9/10. Tighten the weakest checks to improve public safety evidence.
Compare with agentmemory
View Memory & Knowledge Report missing data
96.3
Activity sub-score · out of 100
#7
In Memory & Knowledge

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption. Grade A reflects the trust score band: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Evidence coverage A is separate — it grades how many independent signal types back the score (4 of 5), so a high score on thin evidence stays visible. Full methodology →

Signals refreshed 2026-10-31 08:12 UTC · Repo last pushed today

Rank Trend

2026-09-29 2026-10-31

Activity & Reach

Stars
56.8k
Forks
6.8k
Last Push
2026-10-31
today
Commits (4 wk)
675
Downloads (7d)
20,413
pypi
HN mentions (30d)
1
Open Issues
156
Rank Change
=
was #80

Analysis

Activity Inputs

96.3 / 100
StarsRepository reach
28.5 / 30
FreshnessLast push recency
25.0 / 25
ActivityRecent commits
25 / 25
CommunityFork signal
17.8 / 20

Common questions about Hindsight

Public supply-chain signals for Hindsight are strong: it has multiple independent trust indicators in place. This does not replace your own security review, but Hindsight carries less obvious unverified-evidence risk than projects with thin signals.
Does Hindsight publish package provenance?
Yes. Hindsight's package releases carry build provenance attestations, which cryptographically link the published package back to its source repository and CI workflow.
Does Hindsight have an OpenSSF Scorecard?
Hindsight has an OpenSSF Scorecard score of 4.9/10. 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 Hindsight actively maintained?
Actively maintained. The repository was pushed to within the last 1 day(s).
What license does Hindsight use?
Hindsight ships under MIT. A declared, OSI-approved license is one of the transparency signals HVTrust scores.
Are Hindsight's commits signed?
97% of the last 100 commits to Hindsight 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.

Compare Hindsight head-to-head

Hindsight vs agentmemory → Hindsight vs ReMe → Hindsight vs LanceDB →

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
high confidence
Implemented
Hindsight appears to expose MCP server capabilities.
Detailed evidence is not shown in the public view.
External Service Dependencies
high confidence
1 detected
Public provider/service dependencies detected.
Credential signal: API keys or service config markers documented.
Tool / Plugin Surface
high confidence
Declared
Declared plugin/integration surface detected.
Detailed evidence is not shown in the public view.
Package Provenance Drift
low confidence
Unknown
Package source metadata is missing or inconclusive
Detailed evidence is not shown in the public view.
  • MCP signal live
  • External deps live
  • Tool / plugin surface live
  • Package provenance drift live
How this surface has changed

Detected changes to Hindsight's runtime surface and supply-chain posture, from daily public-signal snapshots. A change here means our detectors see something different — a genuinely changed capability, or better evidence of an existing one.

2026-10-23
Provider Removed
Runtime surface shrank — no longer detected: Anthropic
2026-09-03
Mcp Status Changed
Detected MCP server support changed: declared → implemented

Maintain Hindsight?

For maintainers

HVTrust scores Hindsight 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 7MCP 1Surface 1
2026-10-23
Provider Removed
Runtime surface shrank — no longer detected: Anthropic
2026-10-13
Rank Moved
Rank dropped 14 spots (#81 → #95)
2026-09-26
Rank Moved
Rank rose 11 spots (#82 → #71)
2026-09-23
Rank Moved
Rank dropped 30 spots (#52 → #82)
2026-09-21
Rank Moved
Rank rose 28 spots (#80 → #52)
2026-09-05
Rank Moved
Rank dropped 11 spots (#58 → #69)
2026-09-03
Mcp Status Changed
Detected MCP server support changed: declared → implemented
2026-09-03
Rank Moved
Rank rose 14 spots (#68 → #54)
2026-08-31
Rank Moved
Rank dropped 10 spots (#64 → #74)
GitHub → Website → PyPI: hindsight-api-slim

Embed Badge Badge guide for maintainers →

For maintainers
HVTrust 86.5 Grade A
Markdown:
[![HVTrust](https://hvtracker.net/badge/hindsight.svg)](https://hvtracker.net/agents/hindsight)
HTML:
<a href="https://hvtracker.net/agents/hindsight"><img src="https://hvtracker.net/badge/hindsight.svg" alt="HVTrust"></a>

Other agents in Memory & Knowledge

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