From 86a6f3f52b9f8f04f951651ed3b9bd5963b60727 Mon Sep 17 00:00:00 2001 From: AjayMaan13 Date: Mon, 2 Nov 2026 12:14:57 -0500 Subject: [PATCH] docs: link the example client and show it in the architecture diagram --- README.md | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 0cb8f32..1b7ab0f 100644 --- a/README.md +++ b/README.md @@ -13,6 +13,7 @@ Traces show what happened. AgentTrace tests what caused it: record a run, fork i | API | | | Devpost | | | Pitch deck (PDF) | [docs/AgentTrace-Pitch.pdf](docs/AgentTrace-Pitch.pdf) | +| Example client (separate repo) | : three Claude agents run as a LangGraph graph, recorded into AgentTrace and forkable through a worker | - Built for Build North (Oct 2026), solo. - The free Render services sleep after 15 minutes without traffic, so the first request can take about a minute. The demo page shows the saved results while the API wakes up. @@ -49,13 +50,18 @@ Why a control arm: one replay with a fix that "works" could be luck, because liv ```mermaid flowchart LR subgraph Customer process - W[Workflow + SDK
trace_run, @node, @tool
redacts before send] + G["Your agents
example: agenttrace-harness-demo,
LangGraph + Claude Agent SDK"] + W["AgentTrace SDK
RunRecorder, trace_run, @node, @tool
redacts before send"] + WK["SDK worker
re-runs the agents live for a fork"] + G --> W + G --> WK end subgraph Render API[FastAPI api
ingest, replay, experiments, RCA] WEB[Next.js web
Clerk sign-in] end W -- ingest key --> API + WK -- worker key, asks for fork jobs --> API WEB -- Clerk JWT --> API API --> DB[(SurrealDB Cloud
runs, steps, forks, experiments)] API --> MEM[(SurrealDB Agent Memory
verified failure patterns)] @@ -111,7 +117,7 @@ cd web && npm run dev # http://localhost:3000 Useful scripts (`api/scripts/`): `seed_demo.py` (record the failing run, run the decoy and hero experiments, store the root-cause report), `era_benchmark.py`, `verify_demo.py`, `remember_experiment.py`, `create_workspace_key.py` (mint an ingest key, shown once). Live tests: `RUN_LIVE=1 .venv/bin/pytest`. -Connecting your own agents: sign in, create an organization, then open **Connect your agents**. There you can add the saved example to your workspace (a real run you can fork at once, no code, no tokens), make a key and copy the snippet, or import past logs (those are view only). Agents you did not write can be recorded too, from OpenTelemetry GenAI traces or a LangGraph stream, and given a right or wrong verdict by a check you write (forkable through a worker you run next to your code); an assistant or the command line can look at failed runs through MCP: see [docs/integrations.md](docs/integrations.md) (which also covers failure alerts to Slack and a CI gate) and [docs/self-host.md](docs/self-host.md) to run it yourself. See [sdk/agenttrace_sdk](sdk/agenttrace_sdk) and [record_demo.py](api/scripts/record_demo.py) for a complete example. +Connecting your own agents: sign in, create an organization, then open **Connect your agents**. There you can add the saved example to your workspace (a real run you can fork at once, no code, no tokens), make a key and copy the snippet, or import past logs (those are view only). Agents you did not write can be recorded too, from OpenTelemetry GenAI traces or a LangGraph stream, and given a right or wrong verdict by a check you write (forkable through a worker you run next to your code); an assistant or the command line can look at failed runs through MCP: see [docs/integrations.md](docs/integrations.md) (which also covers failure alerts to Slack and a CI gate) and [docs/self-host.md](docs/self-host.md) to run it yourself. A complete outside example, with its own repo, is [agenttrace-harness-demo](https://github.com/AjayMaan13/agenttrace-harness-demo): a LangGraph app of three Claude agents that records into AgentTrace and runs forks through a worker. See [sdk/agenttrace_sdk](sdk/agenttrace_sdk) and [record_demo.py](api/scripts/record_demo.py) for an example inside this repo. Recording your own workflow in code: @@ -146,7 +152,7 @@ AgentTrace is meant to complement these. What it adds: **control-arm experiments ## Built with -Python 3.11, FastAPI, Pydantic v2, the Anthropic SDK, SurrealDB Cloud and Agent Memory (`surrealdb-memory`), Next.js 16, Clerk, Tailwind, Render, and Era by Eon. The web app started from `create-next-app` and the Clerk quickstart. No LangChain or LangGraph. +Python 3.11, FastAPI, Pydantic v2, the Anthropic SDK, SurrealDB Cloud and Agent Memory (`surrealdb-memory`), Next.js 16, Clerk, Tailwind, Render, and Era by Eon. The web app started from `create-next-app` and the Clerk quickstart. No LangChain or LangGraph in AgentTrace itself; the separate example client above uses LangGraph. ## License