tapes

Transparent agentic telemetry and instrumentation for content-addressable LLM interactions.
About · Download · Documentation · Contributing

· ·

tapes is an Agentic telemetry system for content-addressable LLM interactions. It provides durable storage of agent sessions, plug-and-play OpenTelemetry instrumentation, and deterministic replay of past agent messages.

---

📼 Quickstart

Install tapes:

curl -fsSL https://download.tapes.dev/install | bash

tapes stores sessions in PostgreSQL (with the pgvector extension) and uses an embedding provider to power tapes search. The quickest way to get a local Postgres — plus Ollama for embeddings — is the bundled Docker bootstrap (requires Docker):

tapes local up

For local embeddings, pull the default embeddinggemma model:

ollama pull embeddinggemma

Then start Tapes:

tapes serve

Prefer OpenAI embeddings? Store an API key and switch the embedding provider (tapes local up still provides the required Postgres; Ollama just goes unused):

tapes auth openai
tapes config set embedding.provider openai
tapes serve

You can also provide the key with OPENAI_API_KEY instead of tapes auth openai. When OpenAI is selected without a key, Tapes fails at startup with an authentication configuration error from the OpenAI embedder.

Start a chat session:

tapes chat --model gemma3

Search conversation turns:

tapes search "What's the weather like in New York?"

Checkout a previous conversation state for context check-pointing and retry:

tapes checkout abc123xyz987
tapes chat