linearmemory vs shepherd
Legible persistent agent memory: records observable execution events, consolidates only validated knowledge and explains every relation — MCP server on PostgreSQL 17 with a web explorer. — versus — Runtime substrate that records agent runs as reversible, Git-like execution traces — meta-agents can observe, fork, replay and revert any run before outputs are applied or released.
Both record what an agent did as the primary artifact. Shepherd records runs as reversible execution traces a meta-agent can replay; LinearMemory records observable events and consolidates them into durable, explained knowledge for humans and agents.
| linearmemory | shepherd | |
|---|---|---|
| Stars | 1 | 2.4k |
| Forks | 0 | 206 |
| Language | HTML | Python |
| License | MIT | MIT |
| Last activity | today | 27 days ago |
| Topics | memory, knowledge-graphs | agents, orchestration |
| Curated connections | 3 | 4 |
linearmemory — the curator's take
Interesting for one design choice: memory is a chronological sequence of small observable events (reads, tool calls, decisions, errors, corrections) plus consolidated facts, decisions, procedures and outcomes — never the agent's raw reasoning transcript. Every graph edge carries direction, type, evidence, confidence and a human-readable explanation; humans browse the same store as a story, a relation map or a 3D graph. Postgres is authoritative, the graph projection is rebuildable, Docker Compose brings it up. NOT proven: one star, one author, no benchmark, no adopters yet. Watch it; don't bet on it.
shepherd — the curator's take
The missing 'version control for agent execution': every run becomes a durable trace you can inspect, fork from any step, replay deterministically, or revert — and workspace outputs are held for review before they're applied. If you're building supervision or meta-agents (agents that manage agents), this is the substrate that makes it tractable. NOT mature: early alpha with a moving API and a fresh paper behind it, and the reversibility guarantee only covers what runs inside its coupled agent+environment model — side effects that escaped to the real world don't revert.