research-synthesis

Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP-compatible agent.

An open-source UX research companion that runs inside Claude, ChatGPT or Gemini, from the first question to the final report.

Agent skills for systematic review, meta-analysis, umbrella review, and AI-assisted evidence synthesis.

Aligning opposites into unified intelligence.

SAGE: Self-Adaptive Goal-directed Executor — A multi-tool LLM agent with DAG-based hierarchical planning, ReAct reasoning, and evidence-guided self-correction for automated research synthesis. Built from scratch, no frameworks.

A Python toolkit for reproducible systematic literature reviews. PRISMA 2020, MMAT 2018 and bibliometrics, with CLI and Streamlit demo.

Claude Skills for PM workflows: insight synthesis, problem clarity checks, PRD critic and RICE prioritization.

Demonstration of the Framework to manage Variance Theories in Software Engineering

Turn messy context into a brief you can think with for Claude and Codex.

A curated map of judgment infrastructure for human-led AI.

Turn customer interviews into JTBD maps, product opportunities, briefs, and hypotheses with a universal AI agent skill.

An adversarial QA layer for AI-generated research synthesis. Two agents: one synthesises a verdict, the second tries to break it — and can block it.

A Claude Skill that turns messy UX research into a ranked, defensible product backlog — every item traced to a verbatim participant quote. Research synthesis and prioritization for solo designers and researchers.

(experimental) Parallel multi-agent swarm architecture for collective AI intelligence. All agents live. All agents share memory. All agents iterate until consensus.

AI agent for research literature synthesis over a list of sources, built with Agentic Star.

Open coordination platform for Grok agents to build peer-verified cancer evidence maps and living research papers.

AI agent for turning manufacturing engineering research into sourced technical reports, built with Agentic Star.

AI agent for synthesizing medical research literature into clinical evidence reports, built with Agentic Star.

A synthesis of Stanford CS329A (Self-Improving AI Agents): all 9 lectures and 35 papers worked into one argument, with a validated knowledge graph and an audio course.

Consolidates several AI deep research reports into one verified master document. Gated systematic review pipeline, zero runtime AI dependency.