AllSource vs mem0
mem0 is a memory layer that bolts onto your LLM app. AllSource is a durable event store underneath it — you keep full provenance and time-travel instead of a lossy summary.
| Capability | AllSource | mem0 |
|---|---|---|
Durable event store (survives restart) AllSource Core is the database: a Rust WAL with CRC32 checks, configurable fsync, and columnar Parquet persistence. Event data survives restarts under the selected durability mode. | WAL + Parquet | unknown |
Full event provenance / replay Every change is an immutable event you can replay to reconstruct any past state. | ||
Temporal / as_of queries Point-in-time projections are a first-class query, not a snapshot you have to manage yourself. | ||
Core indexed-read latency Published reference benchmark for Core indexed reads. It does not measure graph, vector, hybrid, or end-to-end agent recall. | 11.9μs (p99) | unknown |
Ingestion throughput Published Core batch-ingest reference. We do not publish competitor throughput figures we cannot verify. | 469K events/sec (reference batch benchmark) | unknown |
Offline / embedded mode Run AllSource in-process as a library — no separate server or network hop required. | ||
MCP tools for AI agents The default tenant connector exposes 55 tools. Fleet and administrative controls bring the exposed total to 73. | 55 tenant / 73 fleet | unknown |
x402 per-call agent payments Native x402 micropayments let agents pay per call instead of negotiating a seat-based contract. | ||
License / self-host Self-host Apache-2.0 Core and community components for free; enterprise components use BSL 1.1. Hosted tiers are optional. | Apache-2.0, self-host | Apache-2.0, self-host |
AllSource figures are from our own benchmarks and documentation. Cells marked “unknown” or “varies” are values we do not publish for mem0 rather than estimate. Based on public documentation; corrections welcome.
Primary sources checked
Pick AllSource if…
- You need every memory write to be auditable and replayable, not summarized away
- You want a published microsecond-range Core indexed-read benchmark, not only a remote memory API
- You want to embed the store in-process or self-host it for free under Apache-2.0
- Your agents pay per call (x402) instead of per seat
Pick mem0 if…
- You want a managed memory abstraction and are happy to self-host the open-source core
- You do not need full event provenance or point-in-time replay
- A higher-level 'remember this' API matters more to you than the underlying store
AllSource vs mem0: FAQ
Build on a durable event store
Start on the hosted Indie plan, or self-host the whole stack for free under Apache-2.0. Either way you keep full event provenance. Published microsecond-range results cover Core indexed reads, not end-to-end memory recall.