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 a derived sessions/traces/spans model for querying and exporting past agent work.

About

Capture is append-only: every intercepted LLM interaction is persisted to an immutable raw_turns log. A pure, idempotent deriver projects that log into the read model — sessions → traces → spans (with span links) — and re-running the deriver simply reproduces the same projection (re-derive prunes anything no longer present down to 0). Derived IDs are deterministic, so the same raw input always yields the same sessions, traces, and spans.

Reads happen over that derived surface: list and inspect sessions (/v1/sessions, cursor-paginated, with model/token/cost/turn-count folds), browse traces and spans (/v1/traces, /v1/sessions/{id}/traces), aggregate at span grain (/v1/stats), and run span-grain semantic search (/v1/search/spans). The original capture is always available verbatim via /v1/sessions/{id}/raw_turns.

Content addressing (the merkle node layer) is retained internally for provenance and dedup; it is not a user-facing browsing surface.

---

📼 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 tapesctl search. The quickest way to get a local Postgres — plus Ollama for embeddings — is the bundled Docker bootstrap (requires Docker):

tapes local up

tapes local up pulls the default embeddinggemma model and writes the Postgres + Ollama connection settings into your .tapes config, so the commands below need no connection flags.

Then start Tapes. tapes serve runs the whole local pipeline together — the proxy (capture), the API, and the derive worker (which projects captured turns into sessions/traces/spans) — so anything you capture becomes browsable automatically. It also embeds spans for tapesctl search by default (disable with --embed-spans=false):

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.

Capturing and reading: tapesctl

tapes is the server. Capturing a session and reading one back are client concerns, and they live in tapesctl:

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

tapesctl never guesses a server. Name this one once so the read commands below work without repeating the flag:

tapesctl config set tapes-url http://localhost:8081

Start with demo data so every command below has something to show — this path works end to end before you wire up a real agent:

tapesctl seed --tapes-url http://localhost:8081

List captured sessions and their ids:

tapesctl sessions list --tapes-url http://localhost:8081

Export a captured session as JSONL — the API's session→traces→spans projection verbatim. tapesctl export is a thin client of GET /v1/sessions/{id}/export, so it needs a running API. The full span tree is included by default; pass --detail traces for turn headers only:

tapesctl export <session-id> --tapes-url http://localhost:8081 -o session.jsonl
tapesctl export <session-id> --detail traces

Search across captured spans (individual main-conversation LLM spans, with their trace and turn context). tapes serve embeds spans by default, so this works out of the box:

tapesctl search "explain the retry logic"

Ready for the real thing? Clear the demo data and point your own agent at the proxy:

tapes local down --wipe && tapes local up   # recreate the DB, clearing the demo
tapesctl start claude --tapes-url http://localhost:8082

tapesctl start launches the agent under a just-in-time capture proxy and ships the turns to this server. Capture addresses the private ingest API on 8082, not the read API on 8081 — a capture pointed at the read port reports success and stores nothing. start launches claude, codex, and pi; the Codex desktop app launches itself and is captured with tapesctl capture codex-app. See Agent integrations for the full matrix and the plugin each lane needs first.

License

Dual-licensed under either of

• Apache License, Version 2.0 (LICENSE-APACHE)
• MIT license (LICENSE-MIT)

at your option. Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed as above, without any additional terms or conditions.