Replaces the paid, rate-limited Zep Cloud service with Graphiti (graphiti-core
0.11.6) backed by a local Neo4j instance — free, unlimited, and self-hosted.
Key changes:
- Add GraphitiAdapter: drop-in Zep-compatible wrapper around Graphiti with a
persistent event-loop thread to avoid asyncio/Neo4j driver conflicts
- Switch LLM client to native GeminiClient + GeminiEmbedder (text-embedding-004
fails on Gemini compat endpoint; use google-genai SDK directly)
- Add _GeminiReranker passthrough replacing OpenAIRerankerClient (which
hardcodes gpt-4.1-nano and uses logprobs unsupported by Gemini)
- Fix Cypher queries: use s.uuid/t.uuid for edge source/target instead of
r.source_node_uuid (null property in Graphiti's schema)
- Add ontology-based entity type classifier (_classify_entity_type) so nodes
get colored by type in the D3 graph visualization instead of all being Entity
- Apply classifier in ZepEntityReader so filter_defined_entities finds entities
(previously 0 personas loaded because all labels were ['Entity'])
- Add startup recovery: auto-mark graph_building projects as graph_completed
on backend restart if Neo4j already has their data
- Add resume capability to graph build: skip already-processed episodes after
a restart (断点续传)
- Add non-blocking graph data cache with background refresh in graph.py
- Add EMBEDDING_MODEL config (default: gemini-embedding-001 for Gemini users)
- Add CLAUDE.md with project architecture and dev commands
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Added signal handling to gracefully manage shutdown events across simulation scripts, ensuring proper cleanup of resources.
- Introduced a global shutdown event to allow simulations to respond to termination signals, improving robustness.
- Suppressed warnings related to multiprocessing resource tracking to avoid unnecessary log clutter during execution.
- Updated cleanup logic in `SimulationRunner` and `ZepGraphMemoryManager` to prevent redundant calls and ensure efficient resource management.
- Enhanced logging to provide clearer feedback during shutdown processes, improving traceability.
- Added context enrichment for actions in `fetch_new_actions_from_db`, providing complete information for posts, comments, and user interactions.
- Introduced a new `_enrich_action_context` function to supplement action arguments with relevant details such as post content, author names, and comment information.
- Updated the `ZepGraphMemoryUpdater` to batch send activities by platform, improving efficiency in processing and logging.
- Enhanced logging to include detailed statistics on sent activities and skipped actions, ensuring better traceability and monitoring of the activity flow.
- Removed content truncation logic from the AgentActivity class, allowing full content to be logged for posts, comments, and quotes.
- Updated the `fetch_new_actions_from_db` function to retain complete content in action arguments, enhancing data accuracy.
- Adjusted simulation scripts to ensure that full content is sent during action creation, improving the representation of agent activities.
- Changed the activity logging format to remove simulation prefixes, ensuring clearer natural language descriptions.
- Updated the `ZepGraphMemoryUpdater` to send activities individually, enhancing the accuracy of entity and relationship extraction.
- Adjusted the README.md to reflect these changes in activity processing and Zep integration, providing clearer instructions for users.
- Added a new optional parameter `enable_graph_memory_update` to the simulation API, allowing real-time updates of agent activities to the Zep knowledge graph.
- Introduced `ZepGraphMemoryUpdater` and `ZepGraphMemoryManager` classes to handle the background processing of activity updates, ensuring efficient API calls and data management.
- Updated the README.md to include detailed instructions on the new graph memory update functionality and its configuration.
- Enhanced the simulation runner to manage the lifecycle of the graph memory updater, including starting and stopping the updater based on user configuration.
- Improved logging to track the status of graph memory updates, providing better insights into the simulation process.
Abhishek Yadav
666ghj