
Cli Anything Chromadb
- 380 installs
- 46.6k repo stars
- Updated August 3, 2026
- hkuds/cli-anything
cli-anything-chromadb is a CLI skill that manages ChromaDB vector database collections, documents, and semantic search queries through a stateless command-line interface built on the ChromaDB HTTP API v2.
About
cli-anything-chromadb is a Claude Code skill providing a stateless command-line interface for ChromaDB vector databases, built on the ChromaDB HTTP API v2 for AI agents and automation workflows. Installed via pip install cli-anything-chromadb, it requires Python 3.10+ and a running ChromaDB server, enabling collection creation, embedding upserts, and semantic queries without a browser UI or one-off scripts. Developers reach for cli-anything-chromadb when building or debugging RAG stores and they need repeatable CLI commands agents can invoke to manage vector collections and run similarity search. It suits backend engineers wiring retrieval-augmented generation pipelines who want agent-native database operations from the terminal.
- ChromaDB collection management
- Embedding upsert and query
- RAG store debugging
- CLI-first vector ops
- cli-anything skill conventions
Cli Anything Chromadb by the numbers
- 380 all-time installs (skills.sh)
- +16 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #152 of 911 Databases skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/hkuds/cli-anything --skill cli-anything-chromadbAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 380 |
|---|---|
| repo stars | ★ 46.6k |
| Last updated | August 3, 2026 |
| Repository | hkuds/cli-anything ↗ |
How do you manage ChromaDB collections from the CLI?
Create collections, upsert embeddings, and query ChromaDB from CLI when agents build or debug RAG stores without writing ad-hoc scripts.
Who is it for?
Backend and AI engineers building RAG pipelines who need agent-invokable ChromaDB operations without writing ad-hoc management scripts.
Skip if: Teams using hosted vector databases other than ChromaDB or workflows that require persistent GUI-based collection administration only.
When should I use this skill?
An agent session needs to create, populate, or query a ChromaDB vector store during RAG pipeline build or debug.
What you get
ChromaDB collections with upserted embeddings and semantic query results returned from CLI commands against the HTTP API v2 server.
- Populated vector collections
- Semantic query results
By the numbers
- Built on ChromaDB HTTP API v2
- Requires Python 3.10+
Files
cli-anything-chromadb
A stateless command-line interface for ChromaDB vector database, built on the HTTP API v2. Designed for AI agents and power users who need to manage collections, documents, and run semantic queries without a browser UI.
Installation
This CLI is installed as part of the cli-anything-chromadb package:
pip install cli-anything-chromadbPrerequisites:
- Python 3.10+
- ChromaDB server running at localhost:8000 (or specify via --host)
Usage
Basic Commands
# Show help
cli-anything-chromadb --help
# Start interactive REPL mode
cli-anything-chromadb
# Check server health
cli-anything-chromadb --json server heartbeat
# List all collections
cli-anything-chromadb --json collection list
# Semantic search
cli-anything-chromadb --json query search --collection hub_knowledge --text "How to deploy"REPL Mode
When invoked without a subcommand, the CLI enters an interactive REPL session:
cli-anything-chromadb
# Enter commands interactively with tab-completion and historyCommand Groups
server
Server health and version commands.
| Command | Description |
|---|---|
heartbeat | Check ChromaDB server health |
version | Get ChromaDB server version |
collection
Manage ChromaDB collections.
| Command | Description |
|---|---|
list | List all collections |
create --name NAME | Create a new collection |
delete --name NAME | Delete a collection |
info NAME | Get collection info |
document
Manage documents in collections.
| Command | Description |
|---|---|
add --collection C --id ID --document TEXT | Add document(s) |
get --collection C | Get documents |
delete --collection C --id ID | Delete document(s) |
count --collection C | Count documents |
query
Semantic search against collections.
| Command | Description |
|---|---|
search --collection C --text T | Semantic search |
Output Formats
All commands support dual output modes:
- Human-readable (default): Tables, colors, formatted text
- Machine-readable (
--jsonflag): Structured JSON for agent consumption
# Human output
cli-anything-chromadb server heartbeat
# JSON output for agents
cli-anything-chromadb --json server heartbeatFor AI Agents
When using this CLI programmatically:
1. Always use `--json` flag for parseable output 2. Check return codes - 0 for success, non-zero for errors 3. Parse stderr for error messages on failure 4. Use `--host` to connect to non-default ChromaDB instances
Version
1.0.0
Related skills
FAQ
What does cli-anything-chromadb require to run?
cli-anything-chromadb requires Python 3.10+, pip install cli-anything-chromadb, and a running ChromaDB server reachable over HTTP API v2. The CLI is stateless and designed for agents managing collections, documents, and semantic queries from the terminal.
How does cli-anything-chromadb differ from using ChromaDB Python SDK directly?
cli-anything-chromadb exposes ChromaDB HTTP API v2 operations as repeatable terminal commands agents can invoke without writing ad-hoc Python scripts. Collection creation, embedding upserts, and semantic queries run from CLI instead of bespoke SDK boilerplate during RAG build and