retrace

Your AI Agent

_

See every LLM call, tool invocation, and error — then replay, fork, or share the full execution as a URL.

uv add retrace · No credit card required

// what retrace does

Record

One @record decorator captures every LLM call, tool invocation, and error as spans in a trace.

1 line to instrument

Replay

Step through agent executions with play, pause, scrub, and speed controls. See every decision.

Frame-by-frame playback

Fork

Branch from any span, modify the input, and watch a new execution path diverge side-by-side.

Git bisect for agents

Share

Publish any trace as an interactive tape URL. Anyone can replay it — no login required.

Shareable via link

Memory

Persistent semantic memory with auto-extraction from traces. Agents remember across runs.

pgvector search

MCP Server

AI coding agents can search traces, recall memories, and inspect executions via MCP protocol.

6 tools available

// how it's different

Existing tools focus on monitoring metrics. Retrace focuses on understanding decisions.

Dashboard of aggregate metrics (latency, error rate)

Step-by-step replay of every individual execution

Log-based tracing — search through JSON spans

Interactive timeline — click any span, see full I/O

No way to test a fix without re-running the agent

Fork from the exact failure point, modify input, re-execute

Share a trace ID — teammate needs platform access

Share a URL — anyone can replay without an account

Framework-locked (LangChain-only or vendor-specific)

Works with any Python/TS agent — OpenAI, Anthropic, Google

Complex setup — SDKs, configs, environment variables

One decorator, one API key — traces flow in 2 minutes

// how it works

FIG 0.1
llm_calltool_callreasoning

See everything

Full visibility into every step your agent takes — inputs, outputs, timing, costs — all in one timeline.

FIG 0.2
forknew path

Debug faster

Find where things went wrong instantly. Branch from any point and try a different approach without rerunning.

FIG 0.3
retrace.io/t/aB3xK

Collaborate

Share any execution as an interactive link. Your team can replay, comment, and learn from every run.

// pricing

Free
$0/mo

For experimenting

  • +500 traces/mo
  • +10 tapes
  • +7-day retention
  • +1 project
  • +Community support
Start free
Pro
$29/mo

For shipping

  • +Unlimited traces
  • +Unlimited tapes
  • +90-day retention
  • +Semantic search
  • +Priority support
Start trial
Enterprise
Custom

For teams

  • +Everything in Pro
  • +SSO / SAML
  • +365-day retention
  • +Dedicated support
  • +SLA guarantee
Contact sales

// questions

How long does setup take?+

Under 2 minutes. Run uv add retrace, add the @record decorator to your agent function, and traces start streaming immediately.

What languages and frameworks are supported?+

Python and TypeScript SDKs with first-class support. Works with any LLM provider (OpenAI, Anthropic, Google AI) and any agent framework (LangChain, CrewAI, Vercel AI SDK, AutoGen, LlamaIndex).

How does forking work?+

Select any span in a trace, modify its input, and Retrace re-executes from that point forward. You get a side-by-side diff showing exactly what diverged — without re-running the entire agent.

Is my data secure?+

All data is encrypted in transit (TLS) and at rest. API keys are SHA-256 hashed and stored securely. We never access your trace data without explicit permission.

What does the free tier include?+

500 traces per month, 10 shared tapes, 7-day retention, and 1 project. No credit card required. Upgrade to Pro ($29/mo) for unlimited traces and 90-day retention.

Can I self-host?+

The Python and TypeScript SDKs are open source. The platform is cloud-hosted, but enterprise customers can discuss private deployment options with dedicated infrastructure.

How is this different from LLM observability tools?+

Most tools show aggregate dashboards — latency charts, error rates, token counts. Retrace lets you replay individual executions step-by-step, fork from any point, and share interactive traces as public URLs.

Does it work with multi-agent systems?+

Yes. Each agent gets its own trace, and spans capture inter-agent communication. You can follow execution across agents in a single timeline.

Start seeing what your agents are doing

Free to start. Under 2 minutes to set up. No credit card required.

uv add retrace