Skip to main content

langchain-goodmem

PyPI License: MIT

LangChain integration for GoodMem — long-term agent memory with semantic storage and retrieval.

GoodMem is a memory layer for AI agents that handles embedding, vector search, reranking, and LLM-powered answering server-side. This package exposes GoodMem operations as LangChain BaseTools that can be wired into any LangChain agent or chain.

Installation

pip install langchain-goodmem

Requires Python 3.10+.

Tools

Tool Description
GoodMemListEmbedders List available embedder models
GoodMemListSpaces List all spaces in your account
GoodMemGetSpace Fetch a single space by ID
GoodMemCreateSpace Create a new space or reuse an existing one
GoodMemUpdateSpace Update name / public-read / labels on a space
GoodMemDeleteSpace Delete a space (cascades to its memories)
GoodMemCreateMemory Store text or files as memories
GoodMemListMemories Paginate memories within a space
GoodMemRetrieveMemories Semantic search with optional reranker / LLM summary
GoodMemGetMemory Fetch a specific memory by ID
GoodMemDeleteMemory Permanently delete a memory

Quick start

from langchain_goodmem import (
    GoodMemCreateSpace,
    GoodMemCreateMemory,
    GoodMemRetrieveMemories,
)

goodmem_kwargs = {
    "goodmem_base_url": "http://localhost:8080",
    "goodmem_api_key": "your-api-key",
}

tools = [
    GoodMemCreateSpace(**goodmem_kwargs),
    GoodMemCreateMemory(**goodmem_kwargs),
    GoodMemRetrieveMemories(**goodmem_kwargs),
]

Use with a LangChain agent

from langchain.chat_models import init_chat_model
from langchain.agents import create_agent

llm = init_chat_model("openai:gpt-4o")
agent = create_agent(llm, tools)

response = agent.invoke({"messages": [{"role": "user", "content": "Save this fact and recall it later."}]})

Retrieve with reranking and LLM summary

GoodMemRetrieveMemories exposes the full server-side post-processor. Set any of these fields to enable reranking, threshold filtering, chronological re-sort, or an LLM-generated abstractReply summary:

result = retrieve.invoke({
    "query": "Which framework develops applications with language models?",
    "space_ids": "space-uuid-1,space-uuid-2",
    "max_results": 5,
    "reranker_id": "reranker-uuid",
    "llm_id": "llm-uuid",
    "llm_temperature": 0.2,
    "relevance_threshold": 0.1,
    "chronological_resort": False,
})

Leave them all unset for plain semantic search.

Environment variables

Variable Description
GOODMEM_BASE_URL Base URL of the GoodMem API server
GOODMEM_API_KEY API key for authentication
GOODMEM_VERIFY_SSL Set to false to skip TLS verification for self-signed dev certs (default: true)

Examples

A live end-to-end smoke test exercising every tool and every post-processor knob is in examples/live_smoke_test.py.

export GOODMEM_BASE_URL=https://localhost:8080
export GOODMEM_API_KEY=...
export GOODMEM_VERIFY_SSL=false
python examples/live_smoke_test.py

License

MIT — see LICENSE.

Download files

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

Source Distribution

langchain_goodmem-0.1.0.tar.gz (106.8 kB view details)

Uploaded Source

Built Distribution

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

langchain_goodmem-0.1.0-py3-none-any.whl (25.2 kB view details)

Uploaded Python 3

File details

Details for the file langchain_goodmem-0.1.0.tar.gz.

File metadata

  • Download URL: langchain_goodmem-0.1.0.tar.gz
  • Upload date:
  • Size: 106.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for langchain_goodmem-0.1.0.tar.gz
Algorithm Hash digest
SHA256 5f5731322cf31ea7cbf6b7fa7bbcecc5a5d3517eb0f0d1e4ecf0d28ee3d1b672
MD5 941119f47bb8e5a5e103e76e255bc04b
BLAKE2b-256 aeee52eb3060d6a97763ffb4070fa6be863ab9b9456ed3ccd66d8cc7e79518dc

See more details on using hashes here.

Provenance

The following attestation bundles were made for langchain_goodmem-0.1.0.tar.gz:

Publisher: release.yml on PAIR-Systems-Inc/goodmem-langchain

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

File details

Details for the file langchain_goodmem-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_goodmem-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 214492a4702e126f7814284a6b5aec4e35ef8dbbc3be4323d14f879ddabb5d8b
MD5 f84a2846fe77e1aa9a9d849891a04dd6
BLAKE2b-256 bfa494236d2f38a4db4320de50adb8c45751c04ea85f867c6a408177f6d171d4

See more details on using hashes here.

Provenance

The following attestation bundles were made for langchain_goodmem-0.1.0-py3-none-any.whl:

Publisher: release.yml on PAIR-Systems-Inc/goodmem-langchain

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

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 files

Supported by

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