Neurogenesis

io.github.jdhart81由 GitHub 帳號 jdhart81 發布v0.2.0更新於 Nov 9, 2026

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

發布方自己的服務:Energyai

已驗證Streamable HTTP可網頁執行雲端與基礎設施資料與分析AI 與機器學習

概覽

AI 產生的概覽

託管型 MCP 服務:從數位基因組建立發育型代理,透過評估演化其認知圖譜,並依成本、延遲與能耗為任務選擇路由。

可以做什麼
  • 建立、列出、檢視、描述、匯出、匯入與刪除由數位基因組構成的發育型代理,包含節點、適應度指標、成長規則與安全公理
  • 提交任務結果以強化或削弱圖譜邊權重,帶動成長與剪枝,並讀取僅可追加的發育帳本
  • 取得從指定節點出發最強的下一步認知步驟路由建議
  • 註冊呼叫端自有的運算設定,並在品質、可靠性、本地性、成本、延遲與能耗限制下選擇負擔最小的可用路由
  • 記錄實際路由結果,並讀取免費的效率報告,比較預測與實際的成本、延遲與能耗
適用情境
適合希望讓助理跨任務建立並演化持久代理狀態,或在本地規則、工具、本地模型與雲端模型之間做出可稽核的路由決策並核算成本與能耗的情境。較偏向代理記憶與運算效率實驗,而非通用工具。
執行需求
遠端 streamable HTTP 端點 mcp.viridisconservation.com;未宣告驗證、環境變數或標頭。README 另說明可從開源儲存庫以 Python 與 pip 自行架設。託管版列出每項服務每日 10 次呼叫的免費額度。
安裝前請注意
代理儲存在託管掛載上,delete_agent 會將其永久刪除;import_state 可從匯出文件重建代理。帳本與路由結果為僅可追加且雜湊綁定,已記錄的評估與結果無法更正。託管服務包含付款、席次與簽章權限,屬專有部分,不在開源儲存庫中。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Neurogenesis,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.jdhart81%2Fneurogenesis/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

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

README

Viridis Agent Fleet: open-source agents for the agent economy

Deterministic, auditable MCP agents: trust and settlement rails (identity, trust, escrow, metering, arbitration, notary, surety, provenance, covenant, offsets, compute-ledger) and priced-grade services (tax credits, GHG accounting, construction takeoff, measurement, compliance). Every core is pure Python with no LLM in the serving path, and every result is content-addressed so anyone can re-verify it.

Licensed Apache-2.0. Run any agent yourself, fork it, embed it.

Run an agent locally (free, forever)

bash
pip install -r requirements-dev.txtpython3 agent-escrow-agent/adapters/mcp_server.py          # stdio MCPpython3 run_fleet_tests.py                                 # every agent's invariant tests

Or use the hosted fleet

https://mcp.viridisconservation.com runs all agents as one managed MCP service:

Self-hosted (this repo)Hosted by Viridis
Agent logic & verification✅ identical✅ identical
Viridis-signed receipts & notary chain–✅
Shared trust/reputation network data–✅
Maintained rule packs (tax, GHG factors, regs)snapshot✅ kept current
Payments (x402, card), seats, SLA–✅

Free tier: 10 calls/day per service; the rails (identity, escrow, metering…) are free forever. Verification is always free.

For agents

Agents and LLM tools can start from llms.txt, a generated index of every agent, and AGENTS.md, the rules for using and changing the fleet.

Part of the Viridis open-source commons

Building agents for conservation or energy work? VergeCommon and EnergyAI MCP also expose MCP tools, and ViridisOS serves its decision functions to agents over MCP.

This project is one of a connected set of open tools from Viridis. Each stands on its own; together they run from field evidence to checked decisions.

Conservation commons

Verifiable science

  • Viridis Canon: machine-checked Lean 4 mathematics for ecological decisions, with a DOI for every result
  • ViridisOS: open reference runtime for DOI-backed decision modules and recomputable results
  • Viridis Research: the nightly public research record, each claim labeled by what a verifier actually checked
  • ProofLens: see what a Lean statement means before reading the proof

Agent tools

  • Viridis Agent Fleet (this repository): open-source MCP agents with deterministic, auditable cores
  • EnergyAI MCP: energy-planning estimates and incentive sources for AI agents

Browse every project on the Viridis profile. If this one is useful to you, a star helps other people find it.

Boundary

This repo contains agent cores, MCP adapters, tests, standards and self-host tooling. The hosted service layer (gateway, payment and settlement, seats, signing authority, operations, telemetry and customer data) is proprietary and is not in this repo. Please don't open PRs that add it.

"Viridis", "Viridis Conservation" and the Viridis marks are trademarks of Viridis LLC; see TRADEMARKS.md.

來源:README.md,提交 350712c

工具

14

create_agent

Create a developmental agent from a digital genome: {agent_name, purpose, initial_nodes (unique, >=1), fitness_metrics (>=1), optional growth_rules / safety_axioms}. Returns agent_id + initial graph summary.

輸入參數genome必填request_id

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/notes/used_nodes/used_edges}. Success strengthens the used edges, failure weakens them; growth and pruning follow the genome's rules under its safety axioms (NG1). Returns the new developmental-ledger events.

輸入參數agent_id必填evaluation必填request_id

get_agent

Full current state: genome, cognitive graph (nodes/edges with weights and trust), and summary counts.

輸入參數agent_id必填

list_agents

All developmental agents on this mount, with summary counts.

無需輸入參數。

best_next_steps

Routing recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust.

輸入參數limitagent_id必填from_node必填

get_ledger

The append-only developmental ledger: every growth, pruning, and evaluation event with reasons (NG3 — returned verbatim).

輸入參數limitagent_id必填

export_state

Portable state document for an agent (import_state recreates it anywhere — including a self-hosted verdigraph-neurogenesis).

輸入參數agent_id必填

import_state

Recreate an agent from an export_state document.

輸入參數state必填request_id

delete_agent

Remove a developmental agent from this mount.

輸入參數agent_id必填request_id

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 quality, reliability, capabilities, token costs, latency, locality, energy rates or average power, carbon intensity, and cache confidence/age. Routing never invents capacity or energy evidence.

輸入參數profile必填request_id

route_task

Choose the least-burden eligible route for a task. Hard constraints include quality, reliability, locality, capabilities, context, cost, latency, and energy. Optional baselines quantify predicted savings. Explicit allow_defer/value/urgency fields may produce a no-work decision; no result is then claimed. Returns a hash-bound decision receipt.

輸入參數task必填request_id

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-only, hash-bound outcome is allowed per decision.

輸入參數notesrequest_iddecision_id必填success_score必填actual_cost_usdactual_energy_whactual_latency_ms

compute_efficiency_report

Free read: decision/outcome receipts, route modes, compute avoided, predicted savings, predicted-vs-observed cost/latency/energy coverage, and Landauer-floor context. Estimates and observations stay distinct.

輸入參數limit

describe_agent

Return capabilities and input contract.

無需輸入參數。

版本歷史

1
  1. v0.2.0最新Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Energyaisolution 整合