anneal-memory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| db | No | Path to the SQLite database file where memory is stored (e.g., './memory.db'). | |
| project_name | No | The name of the project for which memory is being managed. | |
| skip_integrity | No | Bypass tool description integrity verification. Useful for development. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| recordA | Record a typed episode to memory. Call this when important decisions are made, patterns are noticed, tensions are identified, questions arise, or outcomes are observed. Record the reasoning, not just the fact — 'Chose X because Y' is more valuable than 'using X'. Episodes accumulate during a session and serve as raw material for compression into the continuity file at session end. |
| recallA | Query episodes from memory with filters. Call this to find prior context before making decisions, to locate specific episodes for citation during graduation, or to review recent work. Returns matching episodes ordered by timestamp (newest first). Supports time range, type, source, and keyword filters. |
| prepare_wrapA | Prepare a compression package for session wrap. Call this at session boundaries — when work is ending, the user says to wrap up, or the session is getting long. Returns all episodes since the last wrap, the current continuity file, stale pattern warnings, and compression instructions. Marks a wrap as in-progress. After calling, follow the returned instructions to compress episodes into an updated continuity file, then save with save_continuity. The compression step is where the real thinking happens — patterns emerge that weren't visible in the raw episodes. |
| save_continuityA | Validate and save the compressed continuity file. Call this after compressing your episodes using the instructions from prepare_wrap. The text must contain exactly 4 sections: ## State, ## Patterns, ## Decisions, ## Context. The server validates structure, checks graduation citations against real episodes (cited IDs must exist), checks explanation overlap (evidence must reference actual episode content), detects citation gaming (suspicious reuse of single episodes), and may demote ungrounded graduations. Returns validation results and section sizes. |
| statusA | Get memory health metrics. Call this at session start to understand memory state, or when diagnosing issues. Returns episode counts (total and since last wrap), wrap history, continuity file size, episodes by type, and whether a wrap is currently in progress. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Continuity File | The current compressed continuity file — always-loaded agent memory. |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/phillipclapham/anneal-memory'
If you have feedback or need assistance with the MCP directory API, please join our Discord server