DeerFlow vs open-science
DeerFlow leads on trust: 67.3/100 (Grade B) against 62.4/100 (Grade C), a 4.9-point gap. DeerFlow leads on supply-chain integrity and adoption.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Choose DeerFlow if supply-chain integrity and adoption matter most.
- +3.2Safety / Integrity: OSSF Scorecard 6.5 against 3.9
- +2.9Adoption: 82.9k GitHub stars against 4.9k
- +2.2Transparency: OSSF Scorecard 6.5 against 3.9
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
open-science doesn't lead on any scored dimension in this pair.
Where they differ
2 dimensions identical: Identity 10.8 · Maintenance 20.0 · Full evidence table
An independent, evidence-based trust comparison of DeerFlow and open-science, two Research & Data projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | DeerFlowbytedance/deer-flow | open-scienceaipoch/open-science |
|---|---|---|
| HVTrust score | 67.3 | 62.4 |
| Evidence grade | B | C |
| Coverage grade | C | C |
| Overall rank | #391 | #556 |
| Rank in Research & Data | #7 | #9 |
| GitHub stars | 82.9k | 4.9k |
| Last updated | today | today |
| Build provenance | No | No |
| OSSF Scorecard | 6.5 / 10 | 3.9 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 13.1 | 9.9 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 14.0 | 11.8 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 11.8 | 8.9 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 6 — E2B, OpenAI, OpenRouter, … | 1 — Anthropic |
| Requires API keys | Yes | No |
| Plugin surface | extensions | marketplace |
| Provenance drift | — | — |
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 v4.3 →