Co-Researcher
poemswe/co-researcher
Orquestração de agentes para pesquisa acadêmica rigorosa e multi-plataforma
Ver no GitHubSuite profissional de pesquisa acadêmica que orquestra múltiplos agentes especializados para conduzir pesquisa rigorosa. Compatível com Claude Code, Gemini CLI, OpenAI Codex e OpenCode, oferecendo comandos nativos para todas as plataformas.
Instalação
npx convez-ai poemswe/co-researcher1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Pesquisa acadêmica estruturada com análise crítica
- Síntese de literatura e mapeamento de hipóteses
- Proposta de grants e análise de viabilidade
- Avaliação de metodologia e revisão por pares
Veredito

Agent bem construído para pesquisadores que precisam de orquestração inteligente entre múltiplos agentes especializados. Suporte multi-plataforma é robusto, mas exige entendimento técnico para máxima utilidade.
README
A tradução para o português deste README ainda está na fila.
Co-Researcher (v2.1.0)
A professional research suite for conducting rigorous academic research using specialized agents and multi-platform CLI commands. Compatible with Claude Code, Gemini CLI, OpenAI Codex, and OpenCode.
Installation
Claude Code
Option 1: Slash commands
/plugin marketplace add poemswe/co-researcher
/plugin install co-researcher
Option 2: Claude CLI
claude plugin install poemswe/co-researcher
claude plugin install co-researcher
Gemini CLI
Option 1: From GitHub
gemini extension install https://github.com/poemswe/co-researcher
Option 2: From Local Directory
cd /path/to/co-researcher
gemini extension link .
Codex
Option 1: Ask Codex (Agentic) Tell Codex:
Fetch and follow instructions from https://raw.githubusercontent.com/poemswe/co-researcher/main/.codex/INSTALL.md
Option 2: Manual Setup
# 1. Clone this repo to ~/.codex/skills/co-researcher
# 2. Add hook to ~/.codex/AGENTS.md
# 3. Run:
~/.codex/skills/co-researcher/.codex/co-researcher-codex bootstrap
See .codex/INSTALL.md for details.
OpenCode
Option 1: Ask OpenCode (Agentic) Tell OpenCode:
Fetch and follow instructions from https://raw.githubusercontent.com/poemswe/co-researcher/main/.opencode/INSTALL.md
Option 2: Manual Setup
# 1. Clone this repo
# 2. Run the installer:
./.opencode/install.sh
See .opencode/INSTALL.md for details.
Native Platform Parity
The suite provides native research commands across all supported platforms:
| Feature | Command (Claude) | Slash (Gemini) | Skill (Codex) |
|---|---|---|---|
| Research Project | /research | /research | $research |
| Methodology | /methodology | /methodology | $methodology |
| Critical Analysis | /analyze | /analyze | $analyze |
| Bibliography | /bibliography | /bibliography | $bibliography |
| Synthesize | /synthesize | /synthesize | $synthesize |
| Peer Review | /review | /review | $review |
| Ethical Risk | /ethics | /ethics | $ethics |
| Grant Proposal | /grant | /grant | $grant |
Research Orchestration Engine
The /research command features intelligent agent orchestration that automatically:
- Analyzes your research question
- Selects optimal agents for your specific needs
- Creates an execution plan with clear phases
- Coordinates multi-agent workflows
Usage Modes
Interactive Mode (default - recommended):
/research "impact of social media on teenage mental health"
Review and approve the execution plan before agents run.
Auto Mode (for trusted workflows):
/research "climate change mitigation strategies" --auto
Executes the plan automatically without confirmation.
Plan-Only Mode (for review):
/research "AI ethics frameworks" --plan-only
Generates execution plan but doesn't run it.
Example Workflow
# 1. Start research with orchestration
/research "effectiveness of remote work on productivity"
# The engine will:
# - literature-reviewer: Find recent studies on remote work outcomes
# - critical-analyzer: Evaluate methodology and bias in key studies
# - quant-analyst: Interpret effect sizes and statistical significance
# - hypothesis-explorer: Map variables (work location, productivity metrics, confounds)
# 2. Review generated plan and approve execution
# 3. Agents run in coordinated sequence
# 4. Receive integrated findings
Templates
Pre-configured agent combinations for common scenarios:
/research "topic" --template=quick # Fast literature scan
/research "topic" --template=rigorous # Full systematic review
/research "topic" --template=comprehensive # Deep multi-method analysis
Specialized Skills
The suite includes PhD-level research skills, each governed by Systemic Honesty principles.
- critical-analysis: Riguous logic checking and fallacy detection
- ethics-review: IRB compliance and privacy risk assessment
- grant-writing: Funding strategy and proposal development
- hypothesis-testing: Variable mapping and experimental design
- academic-writing: Eliminating AI-isms from research prose
- lateral-thinking: Cross-domain analogies and first-principles reasoning
- literature-review: Systematic search and citation analysis
- multi-source-investigation: Cross-validation across diverse sources
- peer-review: Manuscript critique and methodological review
- qualitative-research: Thematic analysis and coding
- quantitative-analysis: Statistical power and effect size interpretation
- research-manager: Dynamic task scaffolding and polyglot session persistence
- research-methodology: Design selection and validation
- research-synthesis: Narrative synthesis with uncertainty quantification
- systematic-review: PRISMA-standard systematic review guidance
- using-co-researcher: Orients Claude to all available skills in the suite; run once per session to activate the full protocol set
Evaluation Framework
Verify agent performance with the v2.0 benchmark system:
cd evals
python run_eval.py all -j 4 --model "codex:gpt-5.2 high"
Features
- Parallel Runner: Multi-threaded execution with
-j(jobs) flag - Dynamic Rubrics: 6 specialized rubrics matched to agent skills
- Extended Targeting: Support for specific versions and reasoning levels
- Persistent Indexing: Rebuildable
latest/index.mdsummary
Benchmark v2.0
Two-file architecture for scalability and transparency:
Dashboard Data (benchmark_overview.json ~900B):
- Lightweight run metadata and summary stats
- Fast dashboard load times (10-50x improvement)
Test Details (test_results_detail/{run_id}.json ~500KB):
- Full agent outputs and judge evaluations
- Rubric-by-rubric scoring breakdowns
- Must-include analysis and justifications
Arena Dashboard: View live interactive dashboard at coresearcher.poemswe.com
Or run locally:
open evals/index.html
Features: Model leaderboards, capability matrices, score trends, and detailed test breakdowns with performance ratings (Excellent/Good/Fair/Poor).
Architecture
skills/: Specialized research skills (Markdown).commands/: Unified platform commands (.md for Claude, .toml for Gemini)..codex/skills/: Native repository skills for Codex.evals/: 22 test cases and Python runner.- manifests:
gemini-extension.json,AGENTS.md,GEMINI.md.
Star History
License
MIT