Hacktoberfest 2026: as issues que os mantenedores marcaram para outubro, abertas e boas para iniciantes. Ver issues do Hacktoberfest

[bot] Instrument Mem0 (470,878 weekly downloads)

Aberta
  • Algo errado?
#808 0 comentários 0 reações 0 responsáveis Ver no GitHub

Mantenedores costumam responder em até 1 dia

Ninguém assumiu esta issue ainda.

Avaliação

Dificuldade
4/5
Tempo estimado
3-5 dias
Facilidade para iniciantes
68/100
Tipo de issue
Funcionalidade
Clareza
Razoavelmente clara
Status de atividade
Ativa
Stack de tecnologia
python
Domínio
observability

Direção de pesquisa

Start by reading the existing files under py/src/braintrust/integrations/ and py/src/braintrust/wrappers/, then inspect py/noxfile.py and the [tool.braintrust.matrix] section of py/pyproject.toml. Trace the Mem0 Memory and AsyncMemory entry points named in the issue and identify how integrations are registered and tested. Done means add coverage for add, search, and get_all, including their internal LLM and embedding work, with the integration, cassette directory, nox session, and matrix entry described in the issue.

Escrita pelo modelo de indexação a partir do texto da issue.

Descrição

new-integration

Summary

mem0ai (import name mem0, by Mem0) is a widely used persistent-memory layer for LLM agents. Its core Memory class exposes .add(messages, user_id=...) and .search(query, filters={"user_id": ...}) as the primary execution surface. Critically, Memory().add() calls an LLM internally by default (OpenAI gpt-5-mini for fact extraction/updates, plus text-embedding-3-small for embeddings) to extract and consolidate facts from conversation messages before storing them — this is a genuine LLM-driven execution step, not just a database write, and it happens invisibly to Braintrust today.

This repository has zero instrumentation for Mem0 anywhere: no py/src/braintrust/integrations/mem0* directory, no wrapper, no nox session, no cassette directory, and no entry in py/pyproject.toml's [tool.braintrust.matrix].

What's missing

  • Memory.add() / AsyncMemory.add() — stores new memories from a message list; internally triggers an LLM call for fact extraction/update plus an embedding call, both currently untraced.
  • Memory.search() / AsyncMemory.search() — retrieves relevant memories via vector search, filtered by user_id/other filters; the core "memory retrieval" step in an agent's context-assembly loop.
  • Memory.get_all() — full CRUD listing of stored memories for a given filter scope.

Weekly downloads

Weekly downloads: 470,878 (as of 2026-09-28; https://pypistats.org/api/packages/mem0ai/recent)

Braintrust docs status

not_found. Checked https://www.braintrust.dev/docs/guides/tracing and https://www.braintrust.dev/docs/guides/tracing/integrations (both checked 2026-09-28) — neither the tracing-integrations list nor the agent-framework list ("Agno, OpenAI Agents SDK, Claude Agent SDK, Pi Coding Agent SDK, Deep Agents, LangGraph, CrewAI, AutoGen, AgentScope, Google ADK, LiveKit Agents, Mastra, Pipecat, Pydantic AI, Strands Agents SDK, Cloudflare Agents, Cloudflare AI Chat") mentions Mem0.

Upstream sources

Braintrust docs sources checked

Local repo files inspected

  • py/src/braintrust/integrations/ — no mem0/ directory
  • py/src/braintrust/wrappers/ — no Mem0 wrapper
  • py/pyproject.toml [tool.braintrust.matrix] — no mem0ai entry
  • py/noxfile.py — no test_mem0 session
  • Repo-wide case-insensitive grep for import mem0/from mem0/mem0ai under py/src/braintrust/**/*.py — zero matches
Linguagem predominante
Python
Estrelas
20
Forks
18
Merge médio
1d 1h
PRs com merge (30d)
82

Preparar o ambiente

Primeiros passos

  1. Leia a issue inteira e depois o guia de contribuição do projeto.
  2. Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
  3. Faça um fork do repositório e trabalhe em uma branch.
  4. Abra um pull request que referencie o número da issue.

Mais de braintrustdata/braintrust-sdk-python

Todas as issues de braintrustdata/braintrust-sdk-python

Issues semelhantes

Mais issues de Python

Receba novas issues na sua caixa de entrada

Um resumo curto de issues do GitHub para quem está começando.