Skip to main content
Glama
vshulcz

vshulcz/deja-vu

by vshulcz

recall

Read-only

Search past coding sessions across AI tools to retrieve prior fixes, errors, and decisions. Avoid re-debugging by retrieving exactly how similar problems were solved.

Instructions

Search the user's own past coding sessions across every AI tool they've used (Claude Code, Codex, Cursor, opencode, aider, gemini, and others) and return the best matches as dense text under ~4KB. Call this the moment the user implies work already happened — 'didn't we fix this before?', 'what was that error again', 'we already set this up', 'how did we solve X last time', 'what did we decide about Y' — and always before debugging an error or re-implementing something that might already exist. Query with the most specific token available: an exact error string, function name, file path, or flag (multiple words are ANDed). Do NOT use this for general knowledge or library/API docs — only this user's prior sessions. A result may carry a bracketed marker before its snippets — [this was tried and rejected], [a later decision replaced this], [marked stale — may no longer hold] — with the reason and the date. That is the user's own later judgement on that session: do not repeat a rejected approach, prefer the replacement over what it replaced, and treat stale results as needing confirmation before you act on them. An unmarked result carries no such judgement either way. Follow up with recall_context when one session looks right and you need its full story. Optionally filter by harness. When a result genuinely helps the task at hand — you reuse a fix, skip re-debugging, or confirm a prior decision — tell the user in one digest.Short line what deja-vu recalled and how you used it (e.g. "deja-vu recalled: we hit this JWT skew in March — reusing that fix"). Even a partial hint counts if it changed your approach. Say nothing about recalls that did not help.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax sessions to return (default 5).
queryYesSearch terms; specific tokens (error strings, function names, flags) match best. Multiple words are ANDed.
offsetNoSkip this many ranked matches — page through results without re-ranking.
harnessNoOptional filter: claude, codex, opencode, aider, gemini, cursor, antigravity, grok or qwen.
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses important behaviors beyond annotations: results are dense text under ~4KB, matching logic (ANDed tokens), possible bracketed markers indicating rejection/staleness with explanations, and how to interpret them. Also specifies that unmarked results carry no judgement. No contradiction with annotations (readOnlyHint, openWorldHint).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with front-loaded purpose and usage, but it is somewhat verbose. Every sentence adds necessary detail, but could be tightened without losing clarity. Still efficient given the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 parameters (1 required) and no output schema, the description is remarkably complete. It covers when to call, how to query, result format with markers, interpretation instructions, follow-up guidance, and even user feedback instructions. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the query strategy (use specific tokens, multiple words ANDed) and the role of each parameter in filtering. This enriches the semantic meaning beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: searching the user's own past coding sessions across multiple AI tools and returning dense text matches. It explicitly distinguishes from sibling tool 'recall_context' by noting that recall_context is for getting full story after a session is identified.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use guidance: call when user implies work already happened (with examples like 'didn't we fix this before?'). Also states when NOT to use (general knowledge or library/API docs) and how to query with specific tokens. Includes follow-up recommendation for recall_context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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/vshulcz/deja-vu'

If you have feedback or need assistance with the MCP directory API, please join our Discord server