Providers & Agents

17 CrewAI agents, 11 crews, provider chains per role, and the research pipeline.

17 CrewAI Agents

Defined in config/agents.yaml with individual agents/*/SOUL.md files.

#	Agent ID	Role	Delegation
1	lider_orquestador	Orchestrator Lead	✅
2	organizador_archivos	File & Structure Organizer	—
3	product_manager	Product Manager	—
4	director_operaciones	Operations Director	✅
5	bizdev	Business Development	—
6	arquitecto	Software Architect	—
7	developer	Full-Stack Developer	—
8	qa_engineer	QA Engineer	—
9	investigador	Researcher	—
10	devops	DevOps Engineer	—
11	seguridad_blockchain	Blockchain Security Expert	—
12	experto_ideacion	Ideation Expert	—
13	experto_multichain	Multi-Chain Expert	—
14	experto_cuantico	Quantum Computing Expert	—
15	seguridad_informatica	Cybersecurity Expert	—
16	experto_metodologias	Methodologies Expert	—
17	experto_bpm	BPM Expert	—

---

11 Crews

#	Crew	Agents
1	research	Pre-research + 5 agents
2	code-review	QA + Security
3	data	Data Engineer
4	database	Data Engineer + Architect
5	full-mvp	6 agents
6	enigma-audit	Security + QA
7	grant-hunt	Researcher + BizDev
8	content	Narrative
9	daily-ops	Organizer + PM
10	weekly-report	Organizer + Researcher
11	build	Developer + Architect

---

Research Crew Pipeline

Pre-research (5 web searches)
  ↓ real data injected into context
t1: Researcher    (Groq)        → analyzes data
t2: Strategist v1 (Cerebras)   → drafts MVP plan
t3: QA            (Groq)        → verifies with additional searches
t4: Verifier      (Cerebras)   → scores + provides feedback
t5: Strategist v2 (Cerebras)   → produces FINAL improved plan

---

Provider Chains per Role

Primary provider is minimax across all roles. Fallbacks in order:

Role	Chain
code_architect	minimax → groq/kimi-k2 → cerebras → zhipu → nvidia/kimi-k2.5
research_analyst	minimax → groq/llama-3.3 → cerebras → zhipu → nvidia/deepseek
mvp_strategist	minimax → cerebras → groq/llama-3.3 → zhipu → nvidia/qwen3.5
qa_reviewer	minimax → cerebras → groq/llama-3.3 → zhipu → nvidia/deepseek
data_engineer	minimax → cerebras → groq/llama-3.3 → zhipu → nvidia/deepseek
project_organizer	minimax → groq/qwen3-32b → cerebras → zhipu → nvidia/deepseek
narrative_content	minimax → cerebras → groq/llama-3.3 → zhipu → nvidia/deepseek
verifier	minimax → cerebras → groq/llama-3.3 → zhipu → nvidia/deepseek

---

Provider Environment Variables

MINIMAX_API_KEY=         # Primary — 1,000 req/day free
GROQ_API_KEY=gsk_...     # Required — free at console.groq.com
CEREBRAS_API_KEY=        # 1M tokens/day
NVIDIA_API_KEY=          # NIM credits
SAMBANOVA_API_KEY=       # Free large context
OPENROUTER_API_KEY=      # Hermes 405B
GEMINI_API_KEY=          # 20 req/day

---

Temperatures per Role

Role	Temperature	Style
code_architect	0.2	Deterministic
qa_reviewer	0.2	Strict
data_engineer	0.1	Minimal variance
project_organizer	0.3	Structured
research_analyst	0.5	Balanced
mvp_strategist	0.6	Creative
narrative_content	0.7	Creative
verifier	0.2	Deterministic

---

LLM Config Reference

Full provider chain configuration

Mesh Nodes

Local nodes and cloud API nodes