romtuck/openclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
8,017 Commits 258 Branches 39 Tags 276 MiB
0cc3507479
Commit Graph

7 Commits

Author SHA1 Message Date
krejcif
0cc3507479 fix(memory-ruvector): add missing plugin manifest 
Add clawdbot.plugin.json required for config validation to pass.
This fixes test failures in config migration tests.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-26 08:14:16 +01:00
File
9922fdef61 docs(memory-ruvector): highlight benefits over current memory system 
Add compelling comparison tables and feature highlights:
- SONA self-learning vs static memory
- GNN graph intelligence vs flat vectors
- 100x performance improvement
- 10-20x memory efficiency
- ruvLLM adaptive learning capabilities

Make the value proposition clear for PR reviewers.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-26 08:14:01 +01:00
File
a5a42ed3e2 fix(memory-ruvector): address code review security and robustness issues 
- Add Cypher injection protection: validate relationship type is alphanumeric
- Fix metadata type coercion: use nullish coalescing for optional fields
- Add pattern centroid validation: skip malformed patterns in boosting
- Add debug logging to silent catches for better troubleshooting

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-26 08:14:01 +01:00
File
b0b54d0fcd docs(memory-ruvector): remove non-functional remote mode 
Remote mode was documented but the implementation is placeholder only
(random vectors, no HTTP client). This removes misleading documentation
until remote mode is actually implemented.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-26 08:14:01 +01:00
File
ac20e30817 fix(memory-ruvector): register ruvector_learn tool and add link CLI 
Documentation validation fixes:
- Register ruvector_learn tool in local mode (was defined but not registered)
- Add 'clawdbot ruvector link' CLI command (was documented but missing)
- Remove non-existent graph config section from docs

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-26 08:14:01 +01:00
File
a801c7e721 feat(memory-ruvector): add ruvLLM adaptive learning features 
Implements ruvLLM integration with multi-temporal learning:

P0 - Foundation:
- Extended config schema for ruvllm options
- TrajectoryRecorder for search pattern recording
- ContextInjector for agent prompt enrichment
- SONA engine integration with trajectory support

P1 - Learning Core:
- PatternStore with K-means++ clustering
- Search re-ranking using learned patterns
- GraphExpander for automatic edge discovery
- ruvector_recall tool (pattern-aware recall)

P2 - Adaptive Loops:
- BackgroundLoop (30s interval pattern clustering)
- InstantLoop (real-time feedback processing)
- RelationshipInferrer (entity extraction)
- ruvector_learn tool (manual knowledge injection)

P3 - Advanced Features:
- EWCConsolidator (catastrophic forgetting prevention)
- ConsolidationLoop (deep pattern analysis)
- GraphAttention (multi-head context aggregation)
- Pattern export/import CLI commands

Tests: 275 passing (229 + 46 new)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-26 08:14:01 +01:00
File
4670817426 feat(memory): add ruvector vector database plugin 
Add new memory-ruvector extension providing high-performance vector
storage and semantic search capabilities using the ruvector database.

Features:
- Dual-mode operation (remote server or local database)
- Automatic message indexing via hooks
- Semantic search tool for agents
- Multiple embedding providers (OpenAI, Voyage AI, local)
- SONA self-learning for improved search accuracy
- GNN and Cypher graph queries for relationship traversal
- Graceful in-memory fallback
- CLI commands for management

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-26 08:14:01 +01:00