What is chroma-local?

A guide for using Chroma, a tool that stores text as vectors so applications can find similar meaning, on your own computer or server. It covers local clients, local storage, and local setup.

Use it when building semantic search with local Chroma, setting up Chroma with Docker or a local command, choosing an embedding model, or deciding how indexed text and metadata should be stored.

It helps you choose the right connection and storage setup instead of guessing between a server, an embedded test database, or a local service. It also helps keep test data separate from data meant to persist.

chroma-local — Skill for Claude Code and Codex by chroma-core

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add chroma-core/agent-skills --skill chroma-local

Clone the repo

git clone --depth 1 https://github.com/chroma-core/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chroma-core/agent-skills/chroma-local/github.svg)](https://agentmods.dev/skills/chroma-core/agent-skills/chroma-local)

Your own site

<a href="https://agentmods.dev/skills/chroma-core/agent-skills/chroma-local"><img src="https://agentmods.dev/badge/skills/chroma-core/agent-skills/chroma-local/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chroma-core/agent-skills/chroma-local"><img src="https://agentmods.dev/badge/skills/chroma-core/agent-skills/chroma-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,446 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.01446
Opus 5.5	$0.00023	$0.00578
Sonnet 5.5	$0.00011	$0.00289
Haiku 4.5	$0.00006	$0.00145

Measured 1mo ago against content hash 1cf35a462252, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chroma-local scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/chroma-local/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions

Determine these before writing code. Prefer discovering them from the repo and the user request. Ask only when the choice materially changes the implementation.

Runtime shape
- Are they connecting to a running local server, embedding Chroma into tests, or setting up local development from scratch?
- Decide whether they need chroma run, a Docker or service command, HttpClient or ChromaClient, or Python EphemeralClient.
Persistence
- Persistent local data: choose an intentional data path.
- Disposable test data: use defaults or a temp directory.
Embedding model
- Reuse the app's existing embedding provider when possible.
- Otherwise default to @chroma-core/default-embed in TypeScript or the standard local default in Python.
- If the user explicitly wants OpenAI embeddings in TypeScript, install and use @chroma-core/openai.
Indexed data shape
- Determine what is being indexed, how it should be chunked, and what metadata is needed for filtering and updates.

Routing

Existing local server
- Confirm host and port before changing client code.
- Validate the server is reachable before assuming collections are missing.
Fresh local development
- Add a local startup path such as chroma run or the repo's existing Docker or service command.
- Default to localhost:8000 unless the repo already uses another address.
Python tests or disposable local workflows
- Prefer EphemeralClient when persistence is unnecessary.
- Call out that data is lost when the process exits.
Persistent local development
- Use a stable data path and make persistence explicit in code or config.
- Do not silently switch between ephemeral and persistent modes.
Search integration work
- Use getOrCreateCollection() in TypeScript or get_or_create_collection() in Python.
- Design document IDs and metadata so upserts and deletes are straightforward.
- Batch writes when syncing large datasets.

Read the full file on GitHub · 166 lines

Files

What ships with it

15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 166 lines · 57 tokens per session scan A 1cf35a462252

Subscribe to this mod's changes

chroma-local is a skill published in the GitHub repository chroma-core/agent-skills (24 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 1,446 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Databases RAG and vectors

qdrant

Vector search engine for production RAG systems.

NousResearch/hermes-agent · 13 tokens

chroma

Embedding database for RAG and semantic search.

NousResearch/hermes-agent · 12 tokens

pinecone

Managed vector DB for production RAG and search.

NousResearch/hermes-agent · 13 tokens

embeddings

Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.

ruvnet/ruflo · 62 tokens

similarity-search-patterns

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

foryourhealth111-pixel/Vibe-Skills · 30 tokens

pgvector-semantic-search

Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…

timescale/pg-aiguide · 190 tokens