OpenViking vs zvec-grep
Both are Grade A and 0.2 points apart, so choose on what you weigh most. OpenViking leads on supply-chain integrity and adoption.
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Choose OpenViking if supply-chain integrity and adoption matter most.
- +4.0Adoption: 66.8k weekly downloads against 3.6k
- +0.9Safety / Integrity: OSSF Scorecard 6.3 against 5.6
- +0.6Transparency: OSSF Scorecard 6.3 against 5.6
Local-first search across your workspace, built for humans and AI agents.
zvec-grep doesn't lead on any scored dimension in this pair.
Where they differ
2 dimensions identical: Identity 18.0 · Maintenance 20.0 · Full evidence table
An independent, evidence-based trust comparison of OpenViking and zvec-grep, two Memory & Knowledge projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | OpenVikingvolcengine/OpenViking | zvec-grepzvec-ai/zvec-grep |
|---|---|---|
| HVTrust score | 87.6 | 87.4 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #68 | #70 |
| Rank in Memory & Knowledge | #5 | #6 |
| GitHub stars | 41.4k | 4.2k |
| Last updated | today | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 6.3 / 10 | 5.6 / 10 |
| License | AGPL-3.0 | Apache-2.0 |
| Downloads | 67k/wk | 4k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 20.4 | 19.5 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 13.9 | 13.3 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 17.5 | 13.5 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | Declared |
| External providers | 9 — Amazon Bedrock, Anthropic, Firecrawl, … | 1 — Multi-provider (LiteLLM) |
| Requires API keys | No | No |
| Plugin surface | plugins | — |
| Provenance drift | Match | Match |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →