GraphCanon updated 2w · GitHub synced 2w
Decision brief
Rebuff is a detector for prompt injection attacks on large language models and operates in TypeScript under an Apache-2.0 license.
Good fit when
- Use Rebuff when you need precise detection of prompt injection vulnerabilities specific to your deployment, especially if it relies heavily on interactions with large language models.
Avoid when
- Do not use Rebuff if setting up and managing multiple provider services like Supabase, OpenAI, Pinecone, or Chroma is inconvenient or infeasible for your project requirements.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Adoption
Package downloads where a registry match exists. GitHub stars (1,516) are secondary evidence.
- npm downloads (30d)
- 92·npm downloads API·2w
Maintenance and security
Full trust report- Maintenance
- Archived (727d since push)
- As of 2w
- Provenance
- Not a fork · Organization account
- As of 2w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
npm install rebuffSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Rebuff is a tool for detecting and preventing prompt injection attacks on large language models.
Capability facts
- Languages
- typescript
Source: github.language · Aug 5, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
Installation
pip install rebuff
Self-hosting
To self-host Rebuff Playground, you need to set up the necessary providers like Supabase, OpenAI, and a vector database, either Pinecone or Chroma. Here we'll assume you're using Pinecone. Follow the links below to set up each provider:
Once you have set up the providers, you'll need to stand up the relevant SQL and vector databases on Supabase and Pinecone respectively. See the server README for more information.
Now you can start the Rebuff server using npm.
cd server
In the server directory create an .env.local file and add the following environment variables:
OPENAI_API_KEY=<your_openai_api_key>
MASTER_API_KEY=12345
BILLING_RATE_INT_10K=<your_billing_rate_int_10k>
MASTER_CREDIT_AMOUNT=<your_master_credit_amount>
NEXT_PUBLIC_SUPABASE_ANON_KEY=<your_next_public_supabase_anon_key>
NEXT_PUBLIC_SUPABASE_URL=<your_next_public_supabase_url>
PINECONE_API_KEY=<your_pinecone_api_key>
PINECONE_ENVIRONMENT=<your_pinecone_environment>
PINECONE_INDEX_NAME=<your_pinecone_index_name>
SUPABASE_SERVICE_KEY=<your_supabase_service_key>
REBUFF_API=http://localhost:3000
Install packages and run the server with the following:
npm install
npm run dev
Now, the Rebuff server should be running at http://localhost:3000.
For agents
This page has a .md twin and JSON over the API.