Skip to main content

Long-term memory for AI agents — wisdom acquired through experience. Extraction, entity resolution, reconciliation, and retrieval.

Project description

arandu

CI PyPI License: MIT Documentation llms.txt

Long-term memory system for AI agents. Extract facts from conversations, resolve entities, reconcile updates, and retrieve relevant context — works with any LLM provider.

Read the full documentation →

Quickstart

pip install arandu[openai]
import asyncio
from arandu import MemoryClient
from arandu.providers.openai import OpenAIProvider

provider = OpenAIProvider(api_key="sk-...")
memory = MemoryClient(
    database_url="postgresql+psycopg://user:pass@localhost/mydb",
    llm=provider,
    embeddings=provider,
)

async def main():
    await memory.initialize()  # creates tables (idempotent)

    # Write — extracts facts automatically
    result = await memory.write(user_id="user_123", message="I live in São Paulo with my wife Ana")
    print(result.facts_added)  # [{"fact_text": "Lives in São Paulo", ...}]

    # Retrieve — semantic search + keyword + LLM reranking
    context = await memory.retrieve(user_id="user_123", query="where does the user live?")
    print(context.context)  # "## Known facts about the user:\n- Lives in São Paulo ..."

asyncio.run(main())

Requirements

  • Python 3.11+
  • PostgreSQL with pgvector extension
  • An LLM provider (OpenAI included, or implement your own)

Custom Providers

Implement the LLMProvider and EmbeddingProvider protocols to use any backend:

from arandu.protocols import LLMProvider, EmbeddingProvider

class MyProvider:
    async def complete(self, messages, temperature=0, response_format=None, max_tokens=None) -> str:
        ...  # your LLM call

    async def embed(self, texts: list[str]) -> list[list[float]]:
        ...  # your embedding call

    async def embed_one(self, text: str) -> list[float] | None:
        ...  # single text embedding

Configuration

from arandu import MemoryConfig

config = MemoryConfig(
    topk_facts=20,              # max facts to retrieve
    min_similarity=0.20,        # cosine similarity threshold
    min_confidence=0.55,        # minimum fact confidence
    enable_reranker=True,       # LLM reranking of results
    recency_half_life_days=14,  # exponential decay half-life
)

memory = MemoryClient(database_url="...", llm=provider, embeddings=provider, config=config)

Architecture

The SDK implements a 4-stage write pipeline and a 3-signal read pipeline:

Write: Message → Extract (LLM) → Entity Resolution (exact/fuzzy/LLM) → Reconcile (ADD/UPDATE/NOOP/DELETE) → Upsert

Read: Query → Semantic Search (pgvector) + Keyword Search (ILIKE) + Recency Scoring → LLM Rerank → Context Formatting

Documentation

For comprehensive documentation including conceptual guides, configuration reference, and cookbook examples:

https://pe-menezes.github.io/arandu/

Contributing

Contributions are welcome! Please read the Contributing Guide before submitting a pull request.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

arandu-0.13.3.tar.gz (697.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

arandu-0.13.3-py3-none-any.whl (136.7 kB view details)

Uploaded Python 3

File details

Details for the file arandu-0.13.3.tar.gz.

File metadata

  • Download URL: arandu-0.13.3.tar.gz
  • Upload date:
  • Size: 697.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for arandu-0.13.3.tar.gz
Algorithm Hash digest
SHA256 66a43f643609ac7382bfe6f2d5bbae460434987d2c33d77843b33f1102cc09fd
MD5 b29a1bd11648c6205d8cccbc8bb99e82
BLAKE2b-256 e894d5fadb6747376e569fc5221d396ddf11ac26cdb78d45990bfba302b87450

See more details on using hashes here.

Provenance

The following attestation bundles were made for arandu-0.13.3.tar.gz:

Publisher: release.yml on pe-menezes/arandu

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file arandu-0.13.3-py3-none-any.whl.

File metadata

  • Download URL: arandu-0.13.3-py3-none-any.whl
  • Upload date:
  • Size: 136.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for arandu-0.13.3-py3-none-any.whl
Algorithm Hash digest
SHA256 7b0edc1565867fc83992d725fb92f7ac373aaeb7a2657cb3e168b53bff7e3921
MD5 d30519effe5532944c0d96ec543f171a
BLAKE2b-256 9b4134a6934776e5d5f995d23fb9478d4d847413f1a49f2aa0682978155ea8fd

See more details on using hashes here.

Provenance

The following attestation bundles were made for arandu-0.13.3-py3-none-any.whl:

Publisher: release.yml on pe-menezes/arandu

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page