Why Your Agent's Memory Returned Nothing — and How We Fixed Hybrid Recall
AllSource Prime's compressed index reported zero nodes for everything you recorded, and prime_context's L2 tier returned no vectors. Three bugs, one event-sourcing lesson: a projection that isn't fed is a projection that lies. Here's the debugging story, the fix, and the real before/after numbers from the binary.
Write Before You Execute: Building Crash-Safe AI Agents
An agent that crashes mid-task and then re-runs can send the same email twice, create duplicate orders, or push the same commit twice. Here's a single pattern that prevents all of it.
How AllSource Core Works: WAL, Parquet, and DashMap
A deep-dive into AllSource Core's storage architecture. Write-Ahead Log with CRC32 checksums, Parquet columnar persistence, and DashMap concurrent reads. How we get 469K events/sec with zero data loss.
Connecting to AllSource without an SDK
How to ingest, query, stream, and build projections against AllSource using only HTTP and WebSockets — no SDK required. For teams on unsupported languages or anyone who wants to understand the wire protocol.
Direct to Core, or through the gateway? Choosing your connection path
AllSource has one public front door (api.all-source.xyz) and one internal fast path (Core, reachable only inside your network). Picking the right one cuts your p99 in half — picking the wrong one either reimplements rate limits or exposes your event store to the internet.
12μs Agent Memory: How We Got There
From event store to agent memory engine in microseconds. DashMap projections, HNSW vector index, and why the storage layer matters more than the query layer.
Building Agent Memory in Rust: From Event Store to Knowledge Graph
How we built a unified agent memory engine — vectors + graph + compressed index — on top of an event store. Architecture decisions, SOLID refactoring, and why Rust was the right choice.
How a Compressed Index Doubles Cross-Domain Recall
Vector similarity finds X or Y — rarely both. A 500-token markdown index bridges the gap. Here's why, with benchmark data.
Time-Travel Queries Explained
How to reconstruct any entity's state at any point in time with all.source.