Open source deep research TS/JS library with built in web search, reasoning, and bibliography generation
Dynamic multi-agent workflows for Pi — fan a task out across 100s of subagents with model routing, token/cost accounting, resume, git-worktree isolation, an interactive /workflows TUI, /deep-research, and OpenCode-style per-subagent context governance (ma
A deep-research skill that gates every cited claim through a verifier before it enters the report — unlike tools that just cite. Installs into ~/.claude/skills for Claude Code or runs headless. BYOK.
Claude-Code-style dynamic workflows for Pi — fan a task out across 100s of subagents with real model routing, token/cost accounting, resume, git-worktree isolation, an interactive /workflows TUI, and a real /deep-research.
Information-geometric agent memory with mathematical guarantees. 4-channel retrieval, Fisher-Rao similarity, zero-LLM mode, EU AI Act compliant. Works with Claude, Cursor, Windsurf, and 17+ AI tools.
Agent skill for researcher.now: article & video analysis (formatted content + structured claims/facts/quotes) and deep multi-source research returning cited Research Reports. Includes SKILL.md for Hermes/Claude-style skill loaders.
MCP server that lets agents run Webhound reports and datasets, watch long sessions, steer them, diagnose failures, and read cited outputs.
BuiltByEcho Research: local-first web research, browser rendering, source audits, traces, and citation-backed reports.
Shared utilities for Google Gemini AI projects - file upload, MIME validation, operation tracking, and deep research
Deep research from your terminal or your code. Backed by Steel Browser and model providers.
CrawlForge MCP Server - Professional Model Context Protocol server with 26 web scraping, crawling, deep-research, and autonomous-extraction tools. Returns clean Markdown and structured JSON for Claude, Cursor, and any MCP client. Defaults to local Ollama