Biologically-inspired persistent memory engine for Claude Code MCP agents
Zikkaron MCP server exists for a simple reason — assistants are far more useful when they can act on Zikkaron directly instead of describing what you should do. Biologically-inspired persistent memory engine for Claude Code MCP agents.
Your AI forgets you every time you close the tab. Every architecture decision you explained, every debugging rabbit hole you went down together, every "remember, we're using Postgres not SQLite" correction. Gone. You start the next session a stranger to your own tools.
Once Zikkaron is connected, these are the calls the assistant has available:
remember — Store a memory through the predictive coding write gaterecall — Multi-signal retrieval with heat-weighted rankingforget — Delete a memoryvalidate_memory — Check staleness against current file stateget_project_context — Get hot memories for a directoryconsolidate_now — Force a consolidation cyclememory_stats — System statistics across all subsystemsrate_memory — Usefulness feedback for metamemory trackingrecall_hierarchical — Query the fractal hierarchy at a specific abstraction leveldrill_down — Navigate into a memory clustercreate_trigger — Set prospective triggers that fire on matching contextget_project_story — Autobiographical narrative of a projectzikkaron on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Zikkaron's toolset — remember, recall, forget and 11 more — is a fair guide to whether it matches your workflow. It is maintained by amanhij; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| remember | Store a memory through the predictive coding write gate |
| recall | Multi-signal retrieval with heat-weighted ranking |
| forget | Delete a memory |
| validate_memory | Check staleness against current file state |
| get_project_context | Get hot memories for a directory |
| consolidate_now | Force a consolidation cycle |
| memory_stats | System statistics across all subsystems |
| rate_memory | Usefulness feedback for metamemory tracking |
| recall_hierarchical | Query the fractal hierarchy at a specific abstraction level |
| drill_down | Navigate into a memory cluster |
| create_trigger | Set prospective triggers that fire on matching context |
| get_project_story | Autobiographical narrative of a project |
| add_rule | Neuro-symbolic constraints for filtering and re-ranking |
| get_rules | List active rules |
Add to your Claude Code config:
```json
{
"mcpServers": {
"zikkaron": {
"command": "zikkaron"
}
}
}Configuration as documented by the project. Restart the client after saving.
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.