π 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
rUvd90c8fe304ad
diff --git a/README.md b/README.mdindex 529e4f9685..e9e43fd73a 100644--- a/README.md+++ b/README.md@@ -943,28 +943,32 @@ sequenceDiagram</details><details>-<summary>π§ <strong>Memory Architecture</strong> β How knowledge is stored and retrieved</summary>+<summary>π§ <strong>Memory Architecture</strong> β How knowledge is stored, learned, and retrieved</summary>```mermaidflowchart LRsubgraph Input["π₯ Input"]Query[Query/Pattern]+ Insight[New Insight]endsubgraph Processing["βοΈ Processing"]Embed[ONNX Embeddings]Normalize[Normalization]+ Learn[LearningBridge<br/>SONA + ReasoningBank]endsubgraph Storage["πΎ Storage"]HNSW[(HNSW Index<br/>150x faster)]SQLite[(SQLite Cache)]AgentDB[(AgentDB)]+ Graph[MemoryGraph<br/>PageRank + Communities]endsubgraph Retrieval["π Retrieval"]Vector[Vector Search]Semantic[Semantic Match]+ Rank[Graph-Aware Ranking]Results[Top-K Results]end@@ -972,13 +976,26 @@ flowchart LREmbed --> NormalizeNormalize --> HNSWNormalize --> SQLite+ Insight --> Learn+ Learn --> AgentDB+ AgentDB --> GraphHNSW --> VectorSQLite --> VectorAgentDB --> Semantic- Vector --> Results- Semantic --> Results+ Vector --> Rank+ Semantic --> Rank+ Graph --> Rank+ Rank --> Results```+**Self-Learning Memory (ADR-049):**+| Component | Purpose | Performance |+|-----------|---------|-------------|+| **LearningBridge** | Connects insights to SONA/ReasoningBank neural pipeline | 0.12 ms/insight |+| **MemoryGraph** | PageRank + label propagation knowledge graph | 2.78 ms build (1k nodes) |+| **AgentMemoryScope** | 3-scope agent memory (project/local/user) with cross-agent transfer | 1.25 ms transfer |+| **AutoMemoryBridge** | Bidirectional sync: Claude Code auto memory files β AgentDB | ADR-048 |+</details><details>