🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Checkpoint: File edits
rUvdd42b8920e55
diff --git a/v3/implementation/adrs/ADR-051-infinite-context-compaction-bridge.md b/v3/implementation/adrs/ADR-051-infinite-context-compaction-bridge.mdindex 58fca4a0ff..6d97284944 100644--- a/v3/implementation/adrs/ADR-051-infinite-context-compaction-bridge.md+++ b/v3/implementation/adrs/ADR-051-infinite-context-compaction-bridge.md@@ -660,8 +660,9 @@ All capabilities confirmed working (2026-02-10):learnings, and other memory types7. **Self-learning**: Confidence decay + access boosting creates a reinforcement loopwhere frequently useful entries survive and irrelevant entries naturally fade-8. **Semantic search**: 768-dim hash embeddings enable cross-session similarity search- — "What did we discuss about X?" finds relevant turns from any archived session+8. **ONNX semantic search**: 384-dim ONNX embeddings (all-MiniLM-L6-v2) enable true+ semantic cross-session search — "What did we discuss about auth?" finds relevant+ turns from any archived session with real natural language understanding9. **Auto-sync**: SQLite → RuVector migration happens automatically when configured### Negative