Skip to main content
Glama
Sign In
deenesjakoruzh
OpenMesha

OpenMesha

by ANAMIZED
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Hybrid

OpenMesha (OM)

CI License Python 3.11+ MCP SDK CLI API x402

“Autonomous Local Economic System”

🚀 Live Demo

Live Demo

Interactive 14-chapter systems briefing (fully self-contained single file) — kernel, agents, economy, security, quantum, x402, HOTL, and more.

→ Open the live interactive demo

OpenMesha is a production-oriented agentic operating system: Super kernel (Thompson router, bitemporal memory, QAOA/VQE, AgentFence, x402, HOTL, PQC) delivered as a self-contained web control plane, plus a Python control plane with OS-like primitives — agents as processes, budgets, multi-agent workflows, MCP, SDK, and CLI.

A senior engineer who has never seen this repository can, using only the source and this README.md:

  1. Deploy the entire system (single command)

  2. Exercise every major feature

  3. Verify end-to-end correctness via automated checks

Support Agentic OS Kernels ($99) · Agentic OS Cycle ($0.75) · Public Goods Support

Non-custodial USDC (preferred for agents)

Network

Address

Explorer

Base

0xD3d0E9eDAe3Ac7bb199a8EAA761BdA423b878438

basescan

Ethereum

0xD3d0E9eDAe3Ac7bb199a8EAA761BdA423b878438

etherscan

Solana

ETQwWf19axArsY493UfC6bxe2BmEzmzvCb58PPnC38A

solscan

Related: rui · server-os · LRSI · OpenGOS

Related MCP server: meshive-mcp

Surfaces

Surface

Entry

Live Demo (GitHub Pages)

OpenMesha-Briefing-SingleFile.html

Web control plane

web/openmesha.html

REST API

openmesha-api / python -c "from openmesha.main import run; run()"

CLI

openmesha status / openmesha agents ... / openmesha workflow

MCP Server

openmesha-mcp

SDK

from openmesha.sdk import OpenMeshaClient

Multi-agent workflows

POST /v1/workflows · MCP · CLI · skills/multi-agent-workflow/

Skills

skills/*/SKILL.md

CI

.github/workflows/ci.yml

AGENTS.md

Coding-agent contract at repo root

WIRE production path

docs/WIRE.md — full cloud/self-hosted path: architecture, om-ctl API, stack, Foundry economics, settlement, P0–P4 checklists

Quick Start

docker compose up --build
bash scripts/verify.sh

Design principles

  1. Least privilege by construction

  2. Cost is a first-class resource

  3. Fail closed (AgentFence + HOTL)

  4. Honest offline simulation

  5. Deployable with zero tribal knowledge

License

Apache-2.0

Available Tools

9 tools
create_agentA

Create an agent process with intent, USD budget, and capabilities.

Returns agent_id for later run_task / list_agents. Does not execute a goal. Side effect: writes the in-memory process table. Default model is mock-gpt.

Inputs: name (required), intent (required), model, budget_usd, +1 more. Returns: object

create_workflowA

Create specialist agents and run a sequential multi-agent workflow.

Default roles are planner then worker, sharing budget_usd. Use when a goal needs more than one agent. Do not use to run a single existing agent (run_task). Side effects: creates agents + tasks and marks the workflow completed.

Inputs: goal (required), name (required), agents, budget_usd. Returns: object

get_audit_logA

Return governance allow/deny records from AgentFence.

Use after a blocked run_task. Read-only. Not the dollar ledger (get_cost_ledger).

Inputs: no named parameters. Returns: result

get_cost_ledgerA

Return the token/$ cost ledger for this process.

Use to audit spend after run_task. Read-only. Not get_audit_log or get_metrics.

Inputs: no named parameters. Returns: result

get_metricsA

Return runtime counters (agents created, tasks).

Use for health checks. Read-only. Does not include cost rows or policy events.

Inputs: no named parameters. Returns: object

list_agentsA

List in-process agent records (id, status, spend, budget, capabilities).

Use before run_task to discover agent_id values. Read-only snapshot of this process. Does not create agents (create_agent) or start work (run_task).

Inputs: no named parameters. Returns: result

list_available_toolsA

List capability names that can be granted to agents.

Use before create_agent to choose the capabilities argument. Read-only.

Inputs: no named parameters. Returns: result

run_taskA

Run one goal on an existing agent until completion, policy deny, or budget stop.

Blocks up to 120s. Missing agent_id returns an error object. Use create_agent first. Not for multi-agent orchestration (create_workflow). Side effects: task row + spend.

Inputs: goal (required), agent_id (required). Returns: object

x402_payment_quoteA

Return an offline x402 payment quote for a named service.

Read-only simulation. Does not charge or call a facilitator. Missing services return an error object. Not create_agent or run_task.

Inputs: service (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.4/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool targets a distinct action or resource: agent lifecycle, workflow creation, reporting, capability listing, and payment quoting are clearly separated. The get_cost_ledger, get_audit_log, and get_metrics tools explicitly disambiguate their boundaries in their descriptions.

    Naming Consistency4/5

    Most tools follow a clear verb_noun pattern such as list_agents, create_agent, run_task, and get_metrics. The outlier is x402_payment_quote, which is a noun-phrase name with no leading verb, creating a minor inconsistency.

    Tool Count5/5

    Nine tools is a well-scoped count for an agent orchestration and governance server. Each tool addresses a meaningful part of the workflow without feeling redundant or padded.

    Completeness4/5

    The core lifecycle of creating agents, listing agents, running tasks, and creating workflows is covered, along with cost, audit, and metrics reporting. Missing update/delete/stop agent operations are notable but not critically blocking for the apparent in-process simulation scope.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • meshive-mcp

      meshive-mcpofficial

      meshive
      A
      license
      A
      quality
      B
      maintenance
      Enables MCP-capable agents to manage Meshive GPU Cloud resources, including account, workspaces, pods, storage, GPUs, templates, serverless deployments, tasks, assets, machines, and billing history.
      44
      Apache 2.0

    • pai

      connortessaro
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents to manage API keys and child keys with budgets and spending caps, set plans and model routing, handle wallet payments and top-ups, and verify signed receipts through MCP tools.
      265 npm
      2
      MIT