- Conduid
- Marketplace
- #agent-runtime
MCP servers tagged agent-runtime
161 live MCP servers tagged "agent-runtime", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with agent-runtime.
Localharness
High-performance, local-first agent runtime engine in Go. Features WebSocket + Protobuf wire protocol, multi-agent orchestration, interactive TUI, and MCP tools.
Squire
General-purpose runtime for spawning CLI AI agents (Claude Code, Codex, Gemini CLI) as subprocesses with structured event streaming, MCP tool forwarding, and Claude Code permissio…
Agent Kernel
Missing operating-system primitives for agent runtimes: disposable sessions, models as workers, context as virtual memory, artifacts as the system of record. A specification in pr…
Ion
Headless multi-provider LLM agent runtime. Single Go binary, 16+ providers, 59+ extension hooks, zero opinions.
Nimblebrain
Self-hosted platform for MCP Apps and agent automations — tools, interactive UIs, scheduled runs, multi-agent delegation.
Deepseek Harness Handbook
Agent-first, multilingual handbook for DeepSeek Harness: quickstarts, architecture, safety, troubleshooting, and production recipes.
Agent Infrastructure Control Plane
TypeScript/Fastify control plane for agent identity, AgentMail, Stripe cards, event logs, webhooks, MCP, and tool access
Ancilis
Agents change faster than audits. Ancilis discovers what agents can do, classifies the data they touch, activates the right controls, and continuously proves compliance. Trust you…
Seshat
Open-source Go agent runtime for autonomous AI systems and multi-agent automation. MCP, RAG, 15+ LLM providers and 60+ built-in tools in a single binary.
Gro
An LLM agent runtime that treats context like virtual memory: swim-lane paging, semantic retrieval, and an inline stream-marker DSL for runtime control. Multi-provider (Anthropic,…
Harness Fe
The agent that built it never leaves. A source-aware harness for every AI-built app — source-mapped build plugins, an MCP daemon, and a runtime client that let the agent keep watc…
Relay Action Card
Run a Neura Relay Action Card and receive a governed Decision Receipt before execution.
KeelBase
Open-source AI application engineering platform for building business-safe AI applications from existing systems or new business models—with governance, auditability, and private…
Monoid Agent Kernel
Embeddable agent kernel for durable, provider-neutral LLM agents with permissions, pluggable tools, observability, and subagents.
MY GPT
Native macOS MCP runtime for securely connecting ChatGPT and Claude to your Mac.
Codemode Go
Programmatic tool calling for Go agents: the model writes one JavaScript program that calls the tools you already have. A second execution strategy, not a replacement for tool cal…
Agent Runtime Lab
Secure, durable agent runtime in Java: validated DAG execution, sandboxed tools, MCP, approvals, crash recovery, evaluations and measured benchmarks.
Openwar
Discipline layer for CLI agents. Run Claude Code, Codex, and Gemini CLI under one phase-gated runtime with deterministic detectors, replayable traces, persistent memory, and a cha…
HyperTrade
基于通用自主进化内核 (ARC) 的生产级受治理量化交易研究 Agent Runtime，具备 MCTS 搜索、红蓝博弈、归因反思与模拟盘自动上线孵化能力。
Fiasco
Orchestrate the agents. Contain the fiasco. A headless Rust orchestrator for multiple agents and background jobs.
Agent Controller
Declarative runtime for AI agents — define an agent once in YAML (Agent Definition Language) and run the same spec on the Pi, opencode, or Codex runtime through a consistent backe…
Soit
Governed Agent Runtime for Enterprise AI Systems — build, execute, observe, and govern AI agents with permissions, secrets, egress policy, audit, cost, and replay.
MisterSmith
Rust multi-agent orchestration OS with durable sessions, supervised runtime execution, NATS/JetStream messaging, MCP integration, and operator control surfaces
Dreamnet
Open contracts for persistent AI agents: assignments, Capsules, DreamLoops, claims, receipts, and deterministic validation.
Dhms Engine
DHMS / AgentFuse: Execution assurance layer for AI agents — verify tool-call decisions, dispatch boundaries, and execution outcomes.
Zero Context Protocol Python
Python SDK for Zero Context Protocol (ZCP), with native runtime, MCP compatibility, and production transports.
Decision Trace Reconstructor
Post-hoc trace reconstruction for AI agents: turns raw runtime traces into per-property reconstructability reports naming evidenced, missing, and opaque decision facts.
Statepilot
Predictable browser runtime for AI agents with memory, validation, recovery, and MCP integration.
NexusAIAgentFramework
Durable, auditable AI agent runtime with human approval gates, budgets, replay, MCP support and the Open Agent Run format.
Negotium
Self-hosted local AI agent runtime — run Claude Code, Codex, or Maestro with shared memory, skills, vault, and cron schedules, reachable from Terminal, Telegram, and Otium.
Agent Runtime Rust
Protocol-neutral, multi-tenant Rust Agent Runtime with provider routing, tenant-isolated credentials and policies, MCP tools, durable recovery, approvals, and subagents.
Aindy Runtime
Self-hosted runtime for AI agents and workflows. Durable execution, capability-gated tools, human approval gates, and a memory system that accumulates. Runs survive restarts and r…
Stoa Spec
Stoa — the open substrate for agent-readable SaaS. Spec CC-BY-4.0; runtime, SDKs, conformance suite, federated registry all Apache-2.0. By Vext Labs.
Openclaw Codex SDK
Native OpenClaw Codex runtime powered by @openai/codex-sdk
Agent Virtualization
Host-controlled runtime virtualization for autonomous CLI agents
AI Infra Lab Cn
面向中文开发者的 AI Infra 研究、情报与可运行工程实践站。
Little Monkey
Open-source local Agent OS for autonomous AI agents — run local or cloud models with real tools, persistent jobs, sandboxed execution, MCP, and inspectable permissions.
Awesome Agent Os
What an agent needs to live and work on its own — runtimes, computers, memory, skills, reach, identity, and money. A curated, verified list.
Os Loop Bridge
Native companion for OS Loop AI that extends browser agents with secure local capabilities—filesystem access, MCP connectivity, long-running tasks, and system-level execution
Ritsu
Agents as Infrastructure. Self-hosted multi-agent MCP server — long-lived agents with workspaces, persistent memory, and hierarchy. Real admin UI, OAuth 2.1, encrypted secrets at…
Taskplex
TaskPlex — structured workflow orchestration for AI coding agents
Agentruntime
Business-neutral Go agent runtime built on the OpenAI Responses API
Guildai
Guild.ai — independent third-party profile of a public API surface, by API Evangelist. Guild.ai is a control plane for AI agents that lets engineering teams build, deploy, govern,…
Jentic
Jentic — independent third-party profile of a public API surface, by API Evangelist. Jentic is an AI infrastructure company building the agentic knowledge layer for APIs. Founded…
Harnesslab
Record, diff, and gate agent harness behavior as an executable Trace Contract. CI regression tests for lifecycle, tools, approvals, MCP, and adapters.
Myclaw Agent Runtime
Windows-first observable coding-agent runtime with failure recovery, bounded context, replayable traces and MCP tooling.
Claude Meister
Claude Code runtime + global memory + wiki + injector. Cuts per-task token use ~99% in LIGHT mode vs naive load.
Cycles Client Python
Python SDK for Cycles — reserve, commit, release budget and risk for AI agents
Mainsheet
An agents runtime. Define an agent in one file, run it governed, prove what it did. A policy gate decides before every tool call in code the model never sees; budgets cap cost and…
Personal Agent
本地优先的桌面 AI 助手，同时作为 Codex 的受控执行端：以 MCP Server 接入上游，委派任务由本地 Runtime 用自配模型执行；权限默认为空，项目改动先出 diff 并经人工批准。