KYP-MEM
Claude that remembers your conversations AND understands your project.
KYP-MEM gives AI coding agents two-layer memory:
-
Session Memory (Episodic) → remembers what happened across coding sessions
-
Project Intelligence → understands architecture, decisions, docs, and relationships
Your AI agent stops starting from zero every day.
Example
User:
"Why did we move from REST to Kafka?"
Claude:
"In the May 12 session, we found the REST pipeline couldn't handle peak trading volume. We decided to migrate to Kafka for async processing. See [[Architecture Decisions]] and [[Event Pipeline]]."
By intercepting the prompt, KYP-MEM automatically provided the agent with:
- The vectorized semantic search results of past session logs.
- The relevant markdown files from the project knowledge base.
How It Works
KYP-MEM operates as a Model Context Protocol (MCP) server that runs silently in the background, integrating directly with Claude Code.
1. Episodic Memory (Sessions)
Every coding session is automatically captured with full context:
- User prompts (what was asked)
- File reads with content (what was found)
- File edits with diffs (what changed and why)
- Command outputs (what happened)
At session end, Claude Sonnet synthesizes raw activity into a structured summary with Summary, Investigated, Learned, Completed, and Next Steps sections. Sessions are semantically searchable via ChromaDB vector embeddings.
2. Project Intelligence (Vault)
KYP-MEM maintains structured project knowledge as Markdown files with [[wikilinks]]:
- Architecture docs, API references, setup guides
- Known issues, decision history, linked concepts
The agent searches this on-demand via kyp_search when it needs project context.
How It All Connects
- Session Start: Recent session summaries are injected automatically — the agent knows what happened last time.
- During Work: Hooks capture tool activity (reads, edits, commands) with actual content, not just file names.
- Session End: Sonnet synthesizes a rich, semantic summary and saves it to the vault + vector DB.
- Future Sessions: The agent can search past sessions semantically or look up project knowledge on demand.
Installation
npm install -g kyp-mem
That's it. The postinstall script automatically:
- Installs the Python package
- Creates the default vault at
~/.kyp-mem/vault - Registers the MCP server with Claude Code
- Installs session capture hooks
Restart Claude Code and you're ready to go.
Requirements
- Node.js 18+
- Python 3.10+
- Claude Code CLI
- Anthropic API key (for session summarization with Sonnet)
Custom Vault Path
If you want to store your vault somewhere other than ~/.kyp-mem/vault:
kyp-mem init # Interactive prompt to choose vault location
The Agent's Workflow
KYP-MEM embeds behavioral instructions directly into its tools. Without any prompting from you, the agent will automatically:
- Load Context: On session start, it loads recent session summaries so it knows what happened last time.
- Search Before Acting: Before investigating bugs or making decisions, it searches past sessions to avoid repeating work.
- Persist Knowledge: After fixing a bug or making a decision, it updates the project's knowledge base for future sessions.
Web UI
Browse your knowledge graph, view session timelines, and see semantic relationships visually.
kyp-mem ui
Opens at localhost:3333.
CLI Commands
| Command | Description |
|---|---|
kyp-mem init |
Choose vault location (default: ~/.kyp-mem/vault) |
kyp-mem setup-claude |
Register MCP server with Claude Code |
kyp-mem install-hooks |
Enable automatic session capture |
kyp-mem serve |
Start MCP server (stdio, used by the agent) |
kyp-mem ui |
Open the local web UI |
kyp-mem stats |
Print vault statistics |
kyp-mem tree |
Print vault file tree |
kyp-mem config |
View or set configuration (e.g. kyp-mem config session_model) |
kyp-mem doctor |
Check installation and configuration health |
kyp-mem uninstall |
Remove hooks and MCP server from Claude Code |
Uninstall
# Remove from Claude Code (keeps your vault data)
kyp-mem uninstall
# Remove from Claude Code AND delete all data
kyp-mem uninstall --purge
# Remove the npm package
npm uninstall -g kyp-mem
License
MIT
Metadata
Release files for kyp-mem 0.7.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| kyp_mem-0.7.0.tar.gz | 49.4 kB | Without provenance | Details for kyp_mem-0.7.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| kyp_mem-0.7.0-py3-none-any.whl | Python 3 | none | any | Details for kyp_mem-0.7.0-py3-none-any.whl |
Total release size: 100.9 kB
Release files / kyp_mem-0.7.0.tar.gz
| Download URL | kyp_mem-0.7.0.tar.gz |
|---|---|
| Size | 49.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
607d4c8d8277f891fef5b59b5ba32490141b4c72415ae7ebbc2bc97e0217d509
|
|
BLAKE2b-256 checksum How to use checksums |
182285b0a69a6b76a2e4f68790b3be0905bd96df43293e1ea919c6140fa2aea4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Release files / kyp_mem-0.7.0-py3-none-any.whl
| Download URL | kyp_mem-0.7.0-py3-none-any.whl |
|---|---|
| Size | 51.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fecf3cbff523cf48372fa1a5e81ef60d3680b9f21523a256ec9ac4205b493698
|
|
BLAKE2b-256 checksum How to use checksums |
73f7e82d48c81107786910f1a82a47dadbba9ca78b0e209b1bd83cf4106a1ddf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.3
|
Security for kyp-mem 0.7.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.