@joshuaswarren/openclaw-engram 9.0.27 → 9.0.28
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -0
- package/dist/index.js +509 -383
- package/dist/index.js.map +1 -1
- package/openclaw.plugin.json +10 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -33,6 +33,7 @@ AI agents forget everything between conversations. Engram fixes that.
|
|
|
33
33
|
- **Benchmark-first roadmap** — Engram now has an evaluation harness with live shadow recall recording and a CI benchmark delta gate, so memory improvements can be measured and regression-checked instead of argued from anecdotes.
|
|
34
34
|
- **Objective-state recall** — Engram can now store normalized file, process, and tool outcomes and, when `objectiveStateRecallEnabled` is enabled, inject the most relevant objective-state snapshots back into recall context as a separate `Objective State` section.
|
|
35
35
|
- **Causal trajectory graph foundation** — Engram can now persist typed `goal -> action -> observation -> outcome -> follow-up` chains when `causalTrajectoryMemoryEnabled` is enabled and, with `actionGraphRecallEnabled`, emit deterministic action-conditioned edges into the causal graph for later trajectory-aware retrieval.
|
|
36
|
+
- **Causal trajectory recall** — Engram can now, when `causalTrajectoryRecallEnabled` is enabled, inject prompt-relevant causal chains back into recall context as a separate `Causal Trajectories` section with lightweight match explainability.
|
|
36
37
|
- **Zero-config start** — Install, add an API key, restart. Engram works out of the box with sensible defaults and progressively unlocks advanced features as you enable them.
|
|
37
38
|
|
|
38
39
|
## Quick Start
|
|
@@ -186,6 +187,7 @@ Key settings:
|
|
|
186
187
|
| `objectiveStateStoreDir` | `{memoryDir}/state/objective-state` | Root directory for objective-state snapshots |
|
|
187
188
|
| `causalTrajectoryMemoryEnabled` | `false` | Enable the causal-trajectory memory foundation for typed causal chains |
|
|
188
189
|
| `causalTrajectoryStoreDir` | `{memoryDir}/state/causal-trajectories` | Root directory for causal-trajectory records |
|
|
190
|
+
| `causalTrajectoryRecallEnabled` | `false` | Inject prompt-relevant causal trajectories into recall context |
|
|
189
191
|
| `actionGraphRecallEnabled` | `false` | Write action-conditioned causal-stage edges from typed trajectory records into the causal graph |
|
|
190
192
|
|
|
191
193
|
Full reference: [Config Reference](docs/config-reference.md)
|