Registry › Compare › DeerFlow vs WrenAI

DeerFlow vs WrenAI

WrenAI leads on trust: 85.7/100 (Grade A) against 67.2/100 (Grade B), a 18.5-point gap. DeerFlow leads on transparency and maintenance; WrenAI leads on supply-chain integrity and provenance, and rests on broader evidence.

B DeerFlow 67.2

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.

bytedance/deer-flow · #443 overall · #8 Research & Data · coverage C (2/5)

Choose DeerFlow if transparency and maintenance matter most.

+1.4Maintenance
+0.8Transparency: OSSF Scorecard 6.5 against 5.5

A WrenAI 85.7

GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.

Canner/WrenAI · #89 overall · #4 Research & Data · coverage B (3/5)

Choose WrenAI if supply-chain integrity and provenance matter most.

+7.2Identity / Provenance: package provenance attested, against none
+6.0Safety / Integrity: package provenance attested, against none
+1.2Adoption
B vs CEvidence coverage: 3 of 5 independent signal types, against 2

Where they differ

13.1

Safety / IntegrityWrenAI +6.0

19.1

10.8

Identity / ProvenanceWrenAI +7.2

18.0

14.0

TransparencyDeerFlow +0.8

13.2

19.9

MaintenanceDeerFlow +1.4

18.5

11.8

AdoptionWrenAI +1.2

13.0

-2.4

Runtime calibrationWrenAI +6.3

+3.9

Full evidence table

An independent, evidence-based trust comparison of DeerFlow and WrenAI, 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	WrenAICanner/WrenAI
HVTrust score	67.2	85.7
Evidence grade	B	A
Coverage grade	C	B
Overall rank	#443	#89
Rank in Research & Data	#8	#4
GitHub stars	84.9k	18.0k
Last updated	1d ago	1d ago
Build provenance	No	Yes
OSSF Scorecard	6.5 / 10	5.5 / 10
License	MIT	NOASSERTION
Downloads	—	121/wk
Trust dimensions (points earned)
Safety / integrity / 25	13.1	19.1
Identity & provenance / 18	10.8	18.0
Transparency / 17	14.0	13.2
Maintenance / 20	19.9	18.5
Adoption / 20	11.8	13.0
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	6 — E2B, OpenAI, OpenRouter, …	3 — Amazon Bedrock, Anthropic, Postgres
Requires API keys	Yes	No
Plugin surface	extensions	plugins
Provenance drift	—	Match

Open in the live compare tool → DeerFlow profile WrenAI profile More Research & Data →

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 →