mirror/browser
1
0 Fork 0
mirror of https://github.com/lightpanda-io/browser.git synced 2026-10-10 21:33:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

update the README for agent

Browse Source
This commit is contained in:
Pierre Tachoire committed 2026-06-16 17:48:14 +02:00
1 parent c64fb5aa18
commit 208ca4e539
1 file changed
+33 -25
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+33 -25
View File
@@ -149,6 +149,38 @@ await browser.disconnect();
```
</details>
### Agent mode
`lightpanda agent` lets you drive the browser with a native agent. Describe what
you want in plain English or with slash commands, and it controls the browser:
navigating pages, clicking through flows, filling forms, extracting structured
data. Think of it as a robot you're directing to use the web, more than a
chatbot you're having a conversation with.
Because the agent runs inside the same process as the browser, every tool call
is a direct operation and you retain Lightpanda's speed and memory advantage.
The output of an agent session is a
[PandaScript](https://lightpanda.io/docs/usage/pandascript): vanilla JavaScript
with a small set of native browser primitives built directly into Lightpanda.
Run `/save` to export one from your current session, then replay it with
`lightpanda agent <script>.js`. Scripts are deterministic and token-free, so
you can prototype with the LLM and ship the output to production without a
model at runtime.
It supports Anthropic, OpenAI, Gemini, Hugging Face, and local models via
Ollama. You can also run without an LLM using `--no-llm`, which drops you into
the REPL. See the [agent documentation](https://lightpanda.io/docs/usage/agent)
for the full reference.
```console
./lightpanda agent # auto-detects API key from env
./lightpanda agent --task "top story on news.ycombinator.com?"
./lightpanda agent --no-llm # basic REPL, no LLM
./lightpanda agent session.js # run a recorded script
./lightpanda agent --provider gemini --task "..." # force a specific provider
```
### Native MCP and skill
The MCP server communicates via MCP JSON-RPC 2.0 over stdio.
@@ -169,32 +201,8 @@ Add to your MCP configuration:
A skill is available in [lightpanda-io/agent-skill](https://github.com/lightpanda-io/agent-skill).
### Agent mode
`lightpanda agent` runs an interactive agent on top of the same browser. It
supports an LLM-driven REPL (Anthropic, OpenAI, Gemini, Ollama), a one-shot
`--task` mode that prints the answer to stdout, and JavaScript scripts for
recording and deterministically replaying browser sessions. The interactive
REPL remains slash-command based.
To drive Lightpanda from another LLM agent (Claude Code, an MCP-aware client,
etc.), use `lightpanda mcp` above — it exposes the same browser tools without
needing an LLM (or API key) inside Lightpanda.
```console
./lightpanda agent # auto-detects API key from env
./lightpanda agent --task "top story on news.ycombinator.com?"
./lightpanda agent --no-llm # basic REPL, no LLM
./lightpanda agent session.js # run a recorded script
./lightpanda agent --provider gemini --task "..." # force a specific provider
```
See [docs/agent.md](docs/agent.md) for the full reference,
[docs/agent-script.md](docs/agent-script.md) for the JavaScript script format,
or [docs/agent-tutorial.md](docs/agent-tutorial.md) for a step-by-step
end-to-end walkthrough.
### Telemetry
By default, Lightpanda collects and sends usage telemetry. This can be disabled by setting an environment variable `LIGHTPANDA_DISABLE_TELEMETRY=true`. You can read Lightpanda's privacy policy at: [https://lightpanda.io/privacy-policy](https://lightpanda.io/privacy-policy).
## Status