AllSource vs Letta
Letta (formerly MemGPT) gives agents a stateful memory loop. AllSource gives that loop a durable, queryable foundation — full event history with 11.9μs recall instead of memory you have to manage in-context.
| Capability | AllSource | Letta |
|---|---|---|
Durable event store (survives restart) AllSource Core is the database: a Rust WAL (CRC32, fsync) with columnar Parquet persistence. Event data survives restarts. | 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. | ||
Recall latency DashMap-backed in-memory reads over the durable log. Cloud memory APIs typically measure recall in tens of milliseconds. | 11.9μs (p99) | unknown |
Ingestion throughput Lock-free Rust core. We do not publish competitor throughput figures we cannot verify. | 469K events/sec | unknown |
Offline / embedded mode Run AllSource in-process as a library — no separate server or network hop required. | ||
MCP tools for AI agents A Model Context Protocol server ships out of the box for Claude and other MCP clients. | 43 tools | unknown |
x402 per-call agent payments Native x402 micropayments let agents pay per call instead of negotiating a seat-based contract. | ||
License / self-host Run the whole stack yourself for free, or use the hosted tiers. | MIT, self-host | unknown |
AllSource figures are from our own benchmarks and documentation. Cells marked “unknown” or “varies” are values we do not publish for Letta rather than estimate. Based on public documentation; corrections welcome.
Pick AllSource if…
- You want a durable store of record under your agents, not just an in-context memory manager
- You need point-in-time queries and full replay for audit or debugging
- You want microsecond recall and the option to embed or self-host under MIT
- You want per-call (x402) economics for autonomous agents
Pick Letta if…
- You want an opinionated agent runtime with memory management built in
- You are standardizing on Letta's agent abstractions and tooling
- You do not need a separate durable event store of record
AllSource vs Letta: FAQ
Build on a durable event store
Start on the hosted Indie plan for $19/mo, or self-host the whole stack for free under MIT. Either way you keep full event provenance and microsecond recall.