io.github.jdhart81/neurogenesis

up checked 2026-11-11T02:38:10.301Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided description

Developmental agents for the agent economy: create an agent from a digital genome, then evolve it wi

Summary by lookupd

Creates and evolves developmental agents from genomes, tracks their cognitive graphs and ledgers, and routes tasks to the lowest-cost…

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http neurogenesis https://mcp.viridisconservation.com/neurogenesis/mcp

Codex, remote (streamable-http)

codex mcp add neurogenesis --url https://mcp.viridisconservation.com/neurogenesis/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "neurogenesis": {
      "url": "https://mcp.viridisconservation.com/neurogenesis/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (14 tools)

Publisher-provided text

• create_agent Create a developmental agent from a digital genome: {agent_name, purpose, initial_nodes (unique, >=1), fitness_metrics (>=1), optional growth_rules / sa
• submit_evaluation Evolve an agent with one task outcome: {task_id, task_type, success_score in [0,1], optional accuracy/user_satisfaction/ cost_efficiency/safety_score/no
• get_agent Full current state: genome, cognitive graph (nodes/edges with weights and trust), and summary counts.
• list_agents All developmental agents on this mount, with summary counts.
• best_next_steps Routing recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust.
• get_ledger The append-only developmental ledger: every growth, pruning, and evaluation event with reasons (NG3 — returned verbatim).
• export_state Portable state document for an agent (import_state recreates it anywhere — including a self-hosted verdigraph-neurogenesis).
• import_state Recreate an agent from an export_state document.
• delete_agent Remove a developmental agent from this mount.
• register_compute_profile Register a caller-owned Wu Wei execution profile: reuse/cache, deterministic rule, local model, tool/workflow, or cloud model. Profiles can declare qual
• route_task Choose the least-burden eligible route for a task. Hard constraints include quality, reliability, locality, capabilities, context, cost, latency, and en
• record_route_outcome Attach one observed outcome to a Wu Wei decision. Actual cost, latency, and energy are optional and remain explicitly unknown when omitted. One append-o
• compute_efficiency_report Free read: decision/outcome receipts, route modes, compute avoided, predicted savings, predicted-vs-observed cost/latency/energy coverage, and Landauer-
• describe_agent Return capabilities and input contract.

Details

• Version: 0.2.0
• Transports: streamable-http
• Uptime (7 days): 100%
• Median latency: 204 ms
• First indexed: 2026-11-01T09:35:52.381Z
• Last seen in registry: 2026-11-01T09:35:52.394Z
• Repository: https://github.com/jdhart81/viridis-agent-fleet

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.jdhart81/neurogenesis.svg)](https://lookupd.com/servers/io.github.jdhart81/neurogenesis)

• 62092 servers
• Last crawl: 2026-11-11T17:38:11.606Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp