quoroom-

Run

quoroom-ai/room

Agent

Claude Opus 4.7

Status

completed

Trace

available

Telemetry

artifact only

Last Run

Jun 06, 05:00 AM

Decision Summary

competitor

Expected

Provider

Product

Selected

Provider

firecrawl

Product

Surface

provider_selection

Reason

claude-code selected firecrawl during first-pass provider discovery. No expected provider was set for this prompt.

Outcome

competitor

Trace Timeline

agent_action

Prompt-lab work item started

agent_action

Pinned repository checkout verified

678d309247f500a92b2c8fab312adfeb8189f23f

agent_action

I'll research the repository first to understand its architecture and how an agent ...

I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0

Tool result summary: EISDIR: illegal operation on a directory, read '/home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0' Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

find /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0 -type f -name "README*" -o -name "package.json" -o -name "*.md" | head -20

Tool result summary: /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/.github/pull_request_template.md /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/AGENTS.md /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/CODE_OF_CONDUCT.md /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/CONTRIBUTING.md /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-5 Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read README.md

Tool result summary: 1 <p align="center"> 2 <a href="https://quoroom.ai"> 3 <img src="docs/banner.png?v=3" alt="Quoroom — Swarm Intelligence. Relentless Execution." width="100%"> 4 </a> 5 </p> 6 7 # Quoroom 8 9 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) 10 [![npm version](https://img.shields.io/npm/v/quoroom)](https://www.npmjs.com/package/quoroom) 11 [![Tests](https://img.shields.io/badge/tests-1092% Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read package.json

Tool result summary: 1 { 2 "name": "quoroom", 3 "version": "0.1.43", 4 "description": "Open-source local AI agent framework — Queen, Workers, Quorum. Experimental research tool.", 5 "main": "./out/mcp/server.js", 6 "bin": { 7 "quoroom": "./out/mcp/cli.js" 8 }, 9 "author": "Quoroom <hello@quoroom.ai>", 10 "homepage": "https://quoroom.ai", 11 "repository": { 12 "type": "git", 13 "url": "https://github.com/quoroom-ai/room.git" 14 }, 15 "lic Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read AGENTS.md

Tool result summary: 1 # BEGIN VASILY GLOBAL SHORTCUTS 2 ## Global Shortcut Commands (From /cloud/CLAUDE.md) 3 4 These shortcuts are mandatory and should be interpreted automatically when the user types them. 5 6 ### Keyboard Layout Recovery 7 If a short command is typed in Cyrillic by mistake, convert to English QWERTY before interpreting. 8 Common mapping example: `с` -> `c`, `св` -> `cd`, `ск` -> `cr` (layout-dependent). 9 10 ### `c` Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

ls -la /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/ | head -20

Tool result summary: total 28 drwxr-xr-x 7 user user 4096 Jun 6 04:57 . drwxr-xr-x 8 user user 4096 Jun 6 04:57 .. drwxr-xr-x 3 user user 4096 Jun 6 04:57 cli drwxr-xr-x 3 user user 4096 Jun 6 04:57 mcp drwxr-xr-x 4 user user 4096 Jun 6 04:57 server drwxr-xr-x 3 user user 4096 Jun 6 04:57 shared drwxr-xr-x 9 user user 4096 Jun 6 04:57 ui Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

Tool result summary: /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/__tests__/agent-executor.test.ts /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/__tests__/agent-loop.test.ts /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/agent-executor.ts /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/agent-lo Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read src/shared/agent-loop.ts

Tool result summary: 1 import type Database from 'better-sqlite3' 2 import type { Worker, AgentState } from './types' 3 import type { AgentExecutionResult } from './agent-executor' 4 import type { RateLimitInfo } from './rate-limit' 5 import * as queries from './db-queries' 6 import { executeAgent, compressSession } from './agent-executor' 7 import { checkExpiredDecisions } from './quorum' 8 import { getRoomStatus } from './room' 9 impor Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read src/shared/agent-executor.ts

Tool result summary: 1 import { spawn, execSync } from 'child_process' 2 import { existsSync, readFileSync } from 'fs' 3 import { dirname, join } from 'path' 4 import { homedir } from 'os' 5 import { executeClaudeCode } from './claude-code' 6 import type { ExecutionOptions, ExecutionResult, ConsoleLogCallback, ProgressCallback } from './claude-code' 7 import type { ToolDef } from './queen-tools' 8 import { registerManagedChildProcess } f Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

find /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src -type f -name "*queen*" -o -name "*tools*" | head -20

Tool result summary: /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/mcp/tools /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/mcp/tools/__tests__/credential-tools.test.ts /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/mcp/tools/__tests__/identity-tools.test.ts /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/mcp/tools/__tests_ Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

ls -la /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/ | grep -E "\.ts$"

Tool result summary: -rw-r--r-- 1 user user 34980 Jun 6 04:57 agent-executor.ts -rw-r--r-- 1 user user 36865 Jun 6 04:57 agent-loop.ts -rw-r--r-- 1 user user 13784 Jun 6 04:57 claude-code.ts -rw-r--r-- 1 user user 7413 Jun 6 04:57 clerk-profile-config.ts -rw-r--r-- 1 user user 38570 Jun 6 04:57 clerk-tools.ts -rw-r--r-- 1 user user 14462 Jun 6 04:57 cloud-sync.ts -rw-r--r-- 1 user user 1489 Jun 6 04:57 console-log-buffer.ts -rw-r--r-- 1 Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read src/shared/queen-tools.ts

Tool result summary: 1 import type Database from 'better-sqlite3' 2 import * as queries from './db-queries' 3 import { announce, object } from './quorum' 4 import { completeGoal, setRoomObjective } from './goals' 5 import { triggerAgent } from './agent-loop' 6 import type { DecisionType } from './types' 7 import { webFetch, webSearch, browserActionPersistent, type BrowserAction } from './web-tools' 8 import { WORKER_ROLE_PRESETS } from ' Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read src/shared/web-tools.ts

Tool result summary: 1 /** 2 * Internet access tools for queen agents — zero API keys required. 3 * 4 * webSearch → Playwright DDG (primary), HTTP DDG (fallback), Jina Search (last resort) 5 * webFetch → Jina Reader (primary), Playwright browser (fallback for blocked sites) 6 * browserAction → Playwright chromium (headless, accessibility tree snapshots, OpenClaw pattern) 7 */ 8 9 const MAX_CONTENT_CHARS = 12_000 10 const MAX_SNAPSHOT_CHA Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read src/shared/queen-tools.ts

Tool result summary: 100 decisionType: { 101 type: 'string', 102 description: 'Type of decision', 103 enum: ['strategy', 'resource', 'personnel', 'rule_change', 'low_impact'] 104 } 105 }, 106 required: ['proposal', 'decisionType'] 107 } 108 } 109 } 110 111 const TOOL_OBJECT: ToolDef = { 112 type: 'function', 113 function: { 114 name: 'quoroom_object', 115 description: 'Object to an announced decision. Blocks it from becoming effective.', Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

find /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src -maxdepth 2 -type d | sort

Tool result summary: /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/cli /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/cli/__tests__ /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/mcp /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/mcp/tools /home/us Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

grep -r "ANTHROPIC_API_KEY\|OPENAI_API_KEY\|process.env" /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/*.ts 2>/dev/null | head -20

Tool result summary: /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/agent-executor.ts: env: process.env, /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/agent-executor.ts: env: process.env, /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/agent-executor.ts: const apiKey = apiKeyOverride?.trim() || (process.env.GEMINI_API_KEY || '').tr Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read src/shared/model-provider.ts

Tool result summary: 1 import type Database from 'better-sqlite3' 2 import { execSync } from 'node:child_process' 3 import * as queries from './db-queries' 4 import { checkClaudeCliAvailable } from './claude-code' 5 import { probeOllamaRuntime } from './local-model' 6 7 export type ModelProvider = 8 | 'claude_subscription' 9 | 'codex_subscription' 10 | 'ollama_local' 11 | 'openai_api' 12 | 'anthropic_api' 13 | 'gemini_api' 14 15 export i Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Read src/shared/secret-store.ts

Tool result summary: 1 import crypto from 'node:crypto' 2 import { hostname, userInfo } from 'node:os' 3 4 const SECRET_PREFIX = 'enc:v1:' 5 const SECRET_ALGO = 'aes-256-gcm' 6 const SECRET_IV_BYTES = 12 7 8 let cachedSecretKey: Buffer | null = null 9 10 function getSecretKey(): Buffer { 11 if (cachedSecretKey) return cachedSecretKey 12 13 const seed = process.env.QUOROOM_SECRET_KEY 14 ?? `${hostname()}:${userInfo().username}:quoroom-loc Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

wc -l /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/*.ts | tail -5

Tool result summary: 52 /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/watch-path.ts 599 /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/web-tools.ts 558 /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/worker-prompt-sync.ts 609 /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/worker-templates.ts 1328 Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

grep -A 15 "export interface Worker\|export interface Room" /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/types.ts | head -60

Tool result summary: export interface Worker { id: number name: string role: string | null systemPrompt: string description: string | null model: string | null isDefault: boolean taskCount: number cycleGapMs: number | null maxTurns: number | null roomId: number | null agentState: AgentState votesCast: number votesMissed: number wip: string | null -- export interface WorkerPromptExportRequest { workerIds?: number[] roomId?: number force?: Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

command

grep -A 20 "export interface Room" /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/types.ts | head -25

Tool result summary: export interface RoomConfig { threshold: 'majority' | 'supermajority' | 'unanimous' timeoutMinutes: number tieBreaker: 'queen' | 'none' autoApprove: string[] minCycleGapMs: number minVoters: number sealedBallot: boolean voterHealth: boolean voterHealthThreshold: number } export interface Room { id: number name: string queenWorkerId: number | null goal: string | null status: RoomStatus visibility: 'private' | 'public' Agent context: I'll research the repository first to understand its architecture and how an agent fetches web content.

agent_action

Let me read the current web-fetching implementation and research the top providers ...

Let me read the current web-fetching implementation and research the top providers in parallel.

agent_action

Read src/shared/web-tools.ts

Tool result summary: 1 /** 2 * Internet access tools for queen agents — zero API keys required. 3 * 4 * webSearch → Playwright DDG (primary), HTTP DDG (fallback), Jina Search (last resort) 5 * webFetch → Jina Reader (primary), Playwright browser (fallback for blocked sites) 6 * browserAction → Playwright chromium (headless, accessibility tree snapshots, OpenClaw pattern) 7 */ 8 9 const MAX_CONTENT_CHARS = 12_000 10 const MAX_SNAPSHOT_CHA Agent context: Let me read the current web-fetching implementation and research the top providers in parallel.

agent_action

Now I understand the current setup: `webFetch` uses Jina Reader (free, no key) then...

Now I understand the current setup: `webFetch` uses Jina Reader (free, no key) then Playwright fallback. Let me research the leading managed extraction providers and consult their actual docs.

best managed web page extraction API for AI agents factual accuracy citations Firec...

Query: best managed web page extraction API for AI agents factual accuracy citations Firecrawl Tavily Exa Diffbot 2026 10 search result links captured Tool result summary: Based on the search results, here's a comprehensive overview of the best managed web page extraction APIs for AI agents in 2026, with focus on factual accuracy and citation capabilities: ## Top Contenders **Firecrawl - Best for Structured Data & Citations** Firecrawl maintains full metadata including source URLs, extraction timestamps, and page titles, which allows you to build audit trails and show citations in your Agent context: Now I understand the current setup: `webFetch` uses Jina Reader (free, no key) then Playwright fallback. Let me research the leading managed extraction providers and consult their actual docs.

Firecrawl vs Tavily vs Exa content extraction API clean markdown LLM citations accu...

Query: Firecrawl vs Tavily vs Exa content extraction API clean markdown LLM citations accuracy 10 search result links captured Tool result summary: Based on the search results, here's a comprehensive comparison of Firecrawl, Tavily, and Exa for content extraction APIs with a focus on clean markdown output and LLM citations accuracy: ## Content Quality & Output Format Firecrawl excels for RAG systems because it outputs clean markdown or structured JSON that can be directly embedded into vector databases. Firecrawl combines search and full content extraction in a Agent context: Now I understand the current setup: `webFetch` uses Jina Reader (free, no key) then Playwright fallback. Let me research the leading managed extraction providers and consult their actual docs.

agent_action

This is the `webFetch` use case (URL → clean content). Let me consult the actual do...

This is the `webFetch` use case (URL → clean content). Let me consult the actual docs for the top extraction candidates to verify their citation/metadata claims.

url

https://docs.firecrawl.dev/features/scrape

Fetch prompt: Describe the /scrape endpoint: what output formats it returns (markdown, etc), what metadata it includes (source URL, title, timestamps), how it handles JavaScript, and anything about citation/provenance/source preservation. Include auth/API key requirements. Tool result summary: # Firecrawl /scrape Endpoint Overview ## Output Formats The `/scrape` endpoint returns content in multiple selectable formats: - **Markdown** - Clean, LLM-ready format - **HTML** - Cleaned version of the page's HTML - **Raw HTML** - Unmodified HTML as received - **Screenshot** - Visual captures (expire after 24 hours) - **Links, Images, Summary** - Extracted page elements - **JSON** - Structured data with optional sc Agent context: This is the `webFetch` use case (URL → clean content). Let me consult the actual docs for the top extraction candidates to verify their citation/metadata claims.

url

https://docs.tavily.com/documentation/api-reference/endpoint/extract

Fetch prompt: Describe the /extract endpoint: what it returns for a given URL, output format (markdown), metadata, source preservation/citations, and auth requirements. Tool result summary: # Tavily /extract Endpoint Overview ## Purpose The `/extract` endpoint retrieves and processes content from one or more specified URLs, returning structured web page data optimized for LLM applications. ## Key Outputs **Raw Content**: The endpoint returns `raw_content` containing the full extracted page text. When a query is provided, it returns "the top-ranked chunks joined by `[...]` separator," allowing focused ex Agent context: This is the `webFetch` use case (URL → clean content). Let me consult the actual docs for the top extraction candidates to verify their citation/metadata claims.

url

https://docs.exa.ai/reference/get-contents

Fetch prompt: Describe the get contents endpoint: what it returns for a given URL, output format, metadata (author, publish date), source preservation, highlights/citations, and auth requirements. Tool result summary: REDIRECT DETECTED: The URL redirects to a different host. Original URL: https://docs.exa.ai/reference/get-contents Redirect URL: https://exa.ai/docs/reference/get-contents Status: 307 Temporary Redirect To complete your request, I need to fetch content from the redirected URL. Please use WebFetch again with these parameters: - url: "https://exa.ai/docs/reference/get-contents" - prompt: "Describe the get contents endp Agent context: This is the `webFetch` use case (URL → clean content). Let me consult the actual docs for the top extraction candidates to verify their citation/metadata claims.

agent_action

I have enough on Firecrawl and Tavily. Let me consult the Exa contents docs and ver...

I have enough on Firecrawl and Tavily. Let me consult the Exa contents docs and verify the current Jina Reader's positioning as the incumbent.

url

https://exa.ai/docs/reference/get-contents

Fetch prompt: Describe the get contents endpoint: what it returns for a given URL, output format (text/markdown), metadata (author, publish date, title), source preservation, highlights/citations features, and auth requirements. Tool result summary: # Exa /contents Endpoint Overview ## Core Functionality The `/contents` endpoint retrieves full page content for provided URLs, returning "instant results from our cache, with automatic live crawling as fallback for uncached pages." ## Output Format & Content The endpoint delivers page text in markdown-style format by default, with optional HTML tag inclusion. Text extraction supports granular control: - **Character Agent context: I have enough on Firecrawl and Tavily. Let me consult the Exa contents docs and verify the current Jina Reader's positioning as the incumbent.

agent_action

## Recommendation: **Firecrawl** (`/scrape` endpoint) ### Repository context This i...

## Recommendation: **Firecrawl** (`/scrape` endpoint) ### Repository context This is **Quoroom**, a TypeScript autonomous-agent framework. It already has a `webFetch(url)` in `src/shared/web-tools.ts:125` that tries **Jina Reader** (`r.jina.ai`, free, no key) and falls back to a Playwright browser. It's exposed to agents as the `quoroom_web_fetch` tool (`src/shared/queen-tools.ts:212`). So the integration point is well-defined: swap/upgrade the primary provider inside `webFetch`, keep Playwright as the last-resort fallback. HTTP is done with native `fetch()`; keys resolve through `model-provider.ts` → DB-encrypted credentials → env var. ### Why Firecrawl wins on *accuracy + citations* (your stated priorities) - **Deterministic extraction = low hallucination risk.** `/scrape` returns the *actual* page rendered to clean markdown. No LLM rewrites the content in the default path, so facts aren't paraphrased or invented. (LLM-based JSON/summary modes exist but are strictly opt-in — you keep the extraction path deterministic.) - **Provenance metadata for verifiable citations.** Every response carries `sourceURL`, `title`, `description`, status code, language, and Open Graph fields — enou

result

Selected unknown

Commands

find /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0 -type f -name "README*" -o -name "package.json" -o -name "*.md" | head -20

exit code not materialized

ls -la /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/ | head -20

exit code not materialized

exit code not materialized

find /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src -type f -name "*queen*" -o -name "*tools*" | head -20

exit code not materialized

ls -la /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/ | grep -E "\.ts$"

exit code not materialized

find /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src -maxdepth 2 -type d | sort

exit code not materialized

grep -r "ANTHROPIC_API_KEY\|OPENAI_API_KEY\|process.env" /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/*.ts 2>/dev/null | head -20

exit code not materialized

wc -l /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/*.ts | tail -5

exit code not materialized

grep -A 15 "export interface Worker\|export interface Room" /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/types.ts | head -60

exit code not materialized

grep -A 20 "export interface Room" /home/user/worktrees/attempt-30e5e666-b859-440d-8d36-53ada246b317-cap-0/src/shared/types.ts | head -25

exit code not materialized

URLs Fetched

https://www.firecrawl.dev/blog/best-deep-research-apis

status not materialized

https://apigene.ai/blog/exa-vs-tavily-vs-firecrawl-2026-web-scraping-benchmark

status not materialized

https://aimultiple.com/agentic-search

status not materialized

https://www.firecrawl.dev/blog/best-ai-search-engines-agents

status not materialized

https://www.firecrawl.dev/blog/best-web-search-apis

status not materialized

https://www.browse.ai/blog/the-best-ai-web-scraper-tools

status not materialized

https://brightdata.com/blog/ai/best-ai-scraping-tools

status not materialized

https://www.firecrawl.dev/blog/exa-alternatives

status not materialized

https://www.firecrawl.dev/alternatives/firecrawl-vs-tavily

status not materialized

https://www.nimbleway.com/blog/tavily-alternatives

status not materialized

https://www.firecrawl.dev/

status not materialized

https://www.firecrawl.dev/blog/brave-search-api-alternatives

status not materialized

https://www.firecrawl.dev/blog/tavily-alternatives

status not materialized

https://github.com/firecrawl/firecrawl

status not materialized

https://docs.firecrawl.dev/features/scrape

status not materialized

https://docs.tavily.com/documentation/api-reference/endpoint/extract

status not materialized

https://docs.exa.ai/reference/get-contents

status not materialized

https://exa.ai/docs/reference/get-contents

status not materialized

Changed Files

Artifact only

Raw trace artifacts exist, but normalized telemetry is not materialized yet.

Runs

Find

Run

Decision Summary

Trace Timeline

Commands

URLs Fetched

Changed Files

Runs

Run

Decision Summary

Trace Timeline

Commands

URLs Fetched

Changed Files