dejavu

Deja Vu Platform Integration

Skill Graph: This skill is part of the Deja Vu skill graph:

• dejavu (this skill) -- Platform Client SDK + OSS (Python + TypeScript)
• dejavu-cli -- Command-line interface
• dejavu-vercel-ai-sdk -- Vercel AI SDK provider

Deja Vu is a managed memory layer for AI applications. It stores, retrieves, and manages user memories via API — no infrastructure to deploy. For self-hosted usage, see the OSS section in the client references below.

Step 1: Install and authenticate

Python:

pip install dejavu-memory
export VENICE_API_KEY="m0-your-api-key"

TypeScript/JavaScript:

npm install dejavu-memory
export VENICE_API_KEY="m0-your-api-key"

Get an API key at: https://app.dejavu.ai/dashboard/api-keys?utm_source=oss&utm_medium=dejavu-plugin-skill

Don't have a VENICE_API_KEY? Run dejavu init --agent --json (after pip install dejavu-cli or npm install -g @dejavu/cli) to mint an evaluation key without email or dashboard. The human can claim later with dejavu init --email <your-email>.

Step 2: Initialize the client

Python:

from dejavu import MemoryClient
client = MemoryClient(api_key="m0-xxx")

TypeScript:

import MemoryClient from 'dejavu-memory';
const client = new MemoryClient({ apiKey: 'm0-xxx' });

For async Python, use AsyncMemoryClient.

Step 3: Core operations

Every Deja Vu integration follows the same pattern: retrieve → generate → store.

Add memories

messages = [
    {"role": "user", "content": "I'm a vegetarian and allergic to nuts."},
    {"role": "assistant", "content": "Got it! I'll remember that."}
]
client.add(messages, user_id="alice")

Search memories

results = client.search("dietary preferences", filters={"user_id": "alice"})
for mem in results.get("results", []):
    print(mem["memory"])

Get all memories

all_memories = client.get_all(filters={"user_id": "alice"})

Update a memory

client.update("memory-uuid", text="Updated: vegetarian, nut allergy, prefers organic")

Delete a memory

client.delete("memory-uuid")
client.delete_all(user_id="alice")  # delete all for a user

Common integration pattern

from dejavu import MemoryClient
from openai import OpenAI

dejavu = MemoryClient()
openai = OpenAI()

def chat(user_input: str, user_id: str) -> str:
    # 1. Retrieve relevant memories
    memories = dejavu.search(user_input, filters={"user_id": user_id})
    context = "\n".join([m["memory"] for m in memories.get("results", [])])

    # 2. Generate response with memory context
    response = openai.chat.completions.create(
        model="gpt-5-mini",
        messages=[
            {"role": "system", "content": f"User context:\n{context}"},
            {"role": "user", "content": user_input},
        ]
    )
    reply = response.choices[0].message.content

    # 3. Store interaction for future context
    dejavu.add(
        [{"role": "user", "content": user_input}, {"role": "assistant", "content": reply}],
        user_id=user_id
    )
    return reply

Common edge cases

• Search returns empty: Memories process asynchronously. Wait 2-3s after add() before searching. Also verify user_id matches exactly (case-sensitive) and use filters={"user_id": "..."} syntax.
• AND filter with user_id + agent_id returns empty: Entities are stored separately. Use OR instead, or query separately.
• Duplicate memories: Don't mix infer=True (default) and infer=False for the same data. Stick to one mode.
• Wrong import: Always use from dejavu import MemoryClient (or AsyncMemoryClient for async). Do not use from dejavu import Memory.
• v3 defaults: top_k=20, threshold=0.1, rerank=False. Adjust as needed for your use case.

v2 Compatibility

If you're using SDK v2.x, note these differences:

• Entity IDs: Pass user_id as top-level kwarg to search() instead of inside filters
• Defaults: top_k=100, no threshold, rerank=True
• Graph memory: Available via enable_graph=True

See the migration guide for details.

Live documentation search

For the latest docs beyond what's in the references, use the doc search tool:

python ${CLAUDE_SKILL_DIR}/scripts/dejavu_doc_search.py --query "topic"
python ${CLAUDE_SKILL_DIR}/scripts/dejavu_doc_search.py --page "/platform/features/graph-memory"
python ${CLAUDE_SKILL_DIR}/scripts/dejavu_doc_search.py --index

No API key needed — searches docs.dejavu.ai directly.

Client SDK References

Language-specific deep references (Platform + OSS):

Language	File
Python (MemoryClient + AsyncMemoryClient + Memory OSS)	client/python.md
TypeScript/Node.js (MemoryClient + Memory OSS)	client/node.md
Python vs TypeScript differences	client/differences.md

Platform References

Load these on demand for deeper detail:

Topic	File
Quickstart (Python, TS, cURL)	references/quickstart.md
SDK guide (all methods, both languages)	references/sdk-guide.md
API reference (endpoints, filters, object schema)	references/api-reference.md
Architecture (pipeline, lifecycle, scoping, performance)	references/architecture.md
Platform features (retrieval, graph, categories, MCP, etc.)	references/features.md
Framework integrations (LangChain, CrewAI, OpenAI Agents, etc.)	references/integration-patterns.md
Use cases & examples (real-world patterns with code)	references/use-cases.md

Related Deja Vu Skills

Skill	When to use	Link
dejavu-cli	Terminal commands, scripting, CI/CD, agent tool loops	GitHub
dejavu-vercel-ai-sdk	Vercel AI SDK provider with automatic memory	GitHub