# philippgille/chromem-go

Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence.

Repository: https://github.com/philippgille/chromem-go
Canonical: https://ross.abutalabs.com/products/chromem-go
Language: Go
License: MPL-2.0
License Family: copyleft
Topics: embeddings, go, golang, llm, llms, nearest-neighbor, rag, retrieval-augmented-generation, vector-database, vector-search, chroma, chromadb, embedded, in-memory, cosine-similarity
Last push: 2026-05-17T18:00:12+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 82, release rhythm 8, longevity 70
- inputs: {"age_days": 983, "days_push": 108, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1048, forks 75 (observed 2026-08-28T04:03:22.418539+00:00)

## What it is
chromem-go is an embeddable vector database for Go with a Chroma-like interface and zero third-party dependencies. It runs in-memory with optional persistence, enabling RAG and embeddings-based features without running a separate database server.

## Use cases
- add rag to my go app without running a separate vector database
- store and search document embeddings in-process
- build a question answering system over private documents
- implement semantic text or code search
- build a recommendation system with embeddings
- classify or cluster documents by similarity

## When to choose
- you want an embedded vector store like SQLite instead of a standalone database
- your dataset is small to medium (up to ~100k documents) and query latency matters
- you want zero third-party dependencies in your Go project
- you want a Chroma-like API in pure Go

## When to avoid
- you need to scale to millions of documents or distributed deployment
- you need advanced database features like filtering, sharding, or replication
- you need a stable API before v1.0.0 since breaking changes may occur
- you need a client library to connect to an actual Chroma server

## Facets
- artifact type: library
- maturity: experimental
- function: vector-database, search-engine, rag
- domain: databases, large-language-models, machine-learning
- platform: go, cross-platform
- tags: embeddings, vector-search, in-memory, chroma-compatible, embeddable, cosine-similarity, nearest-neighbor, persistence, search, retrieval-augmented-generation

## Member repositories
- philippgille/chromem-go (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:22.418539+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:00:48.757331+00:00, confidence not recorded.
  - readme: https://github.com/philippgille/chromem-go (fetched 2026-08-28T04:03:22.418539+00:00, sha 01de95dd8344)
- Data as of 2026-08-30T08:39:29.467469+00:00.