Mmcp.market

Head to head

Agent-Native Chat vs three.ws Provenance

Same numbers we show everywhere else, lined up. Ratings come from users, the grade comes from our scanner, adoption comes from public registries.

Agent-Native Chatio.github.BuilderIO/agent-native-chat
A
No reviews yet

Minimal chat-first app with durable threads, actions, and the app-agent loop

Full listing
three.ws Provenanceio.github.nirholas/provenance-mcp
B
No reviews yet

Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.

Full listing

The short version

Neither has been reviewed yet, so the comparison rests on the scan and the public usage numbers. The safety scan favours Agent-Native Chat (98/100 against 83). Agent-Native Chat is hosted and callable through the gateway; three.ws Provenance runs on your own machine.

 Agent-Native Chatthree.ws Provenance
User ratingNo reviews yetNo reviews yet
Safety gradeA98/100B83/100
AdoptionEstablishedEstablished
GitHub stars4.9k206
Downloads / week–29
Runs whereHosted (remote)Your machine (local)
Gateway-readyYesNo
Tools——
Write actions——
Price per callFreeFree
Licence—Apache-2.0
Last release2026-09-192026-09-22
CategoryAI and agentsAI and agents

Other comparisons

Agent-Native Chat vs Basic MemoryAgent-Native Chat vs MCPAgent-Native Chat vs Local RagAgent-Native Chat vs Ts CoreAgent-Native Chat vs Emilia ProtocolAll AI and agents servers