code-review-graph
MCPMIT
Local-first code intelligence graph for MCP and CLI, reducing AI context by up to 71x.
31k·Developer Tools·Open source
hyperresearch
MCPOpen sourceDeep research skill for Claude Code and Codex that builds a persistent, searchable research vault.
3.8kMIT
Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai
Pros
- +16-step tier-adaptive pipeline with adversarial auditing and verified citations
- +Persistent markdown+SQLite vault that compounds across sessions
- +Eight scholarly sources unified in one deduplicated query layer
- +Resumable runs and scales from 30-minute fast paths to dissertation-length reports
Cons
- −Requires Claude Code or OpenAI Codex plus local Python install
- −Codex support still pending PyPI release, needs GitHub install
- −Benchmark leadership is an internal projection pending third-party validation
Target audience: Researchers, analysts, and developers using Claude Code or Codex who need auditable, source-backed deep research.
Related tools
Other open-source tools that share tags with hyperresearch.
ai-berkshire
MCPMIT
AI-era value investing research framework for Claude Code/Codex, using 4 masters' methodologies and multi-agent adversar
16k·AI Agents·Open source
memU
MCPNOASSERTION
memU is a lightweight, agent-driven memory system that gives users a shared LLM wiki across sessions, agents, and device
14k·MCP Servers·Open source
EverOS
MCPApache-2.0
Local-first, Markdown-native memory layer for AI agents with SQLite and LanceDB indexing.
12k·MCP Servers·Open source
MemOS
MCPApache-2.0
Self-evolving memory OS for LLM & AI agents with hybrid retrieval, multi-modal memory, and 35% token savings.
11k·MCP Servers·Open source
valuecell
MCPApache-2.0
Community-driven multi-agent platform for financial applications with AI agents for stock selection, research, and tradi
11k·AI Agents·Open source