All Agent Runtime tools (43)
- A2A ProtocolOpen agent-to-agent protocol. Spec is $0.
- agentmemoryPersistent, searchable memory for AI coding agents with 95.2% recall on LongMemEval, running locally on SQLite with MCP, hooks, and 54 tools for Claude Code,.
- AgentOpsAgent session replay and traces. Free $0. Pro is $40/month. Enterprise is custom. GitHub is about 4.4k stars, not 5k+ unspecified.
- AlloomiMeland Labs workspace that turns expert methods into a self-evolving digital employee. Early access v0.6.1. Free, Basic $15/mo, Pro $39/mo.
- browser-useOpen-source Python library that makes websites accessible to AI agents, letting them drive a real browser to click, type, and fill forms.
- BrowserbaseHosted browser infra for agents. Developer is $20/month. Startup is $99/month. Scale starts at $249/month after a custom form.
- CC Safety NetA PreToolUse hook that blocks destructive Git and file commands and secret access before AI coding agents run them, defeating reordered flags, shell wrappers, and one-liners.
- Cloudflare ComputerPreview MIT agent filesystem on Durable Objects. Not production. Pay Workers usage, not a $0 computer SKU.
- CrewAIPython multi-agent framework with crews, flows, and an Enterprise Cloud from $99/seat. AMP is now that cloud, not a separate product name.
- DaytonaDaytona is now a closed-source sandbox cloud. GitHub is archived. Starter $20, Plus $200, Scale $500, plus compute after included credits.
- DeepSeek HarnessMIT agent runtime. Pay model API only. Live Flash peak $0.44/$1.32 per 1M, not the old $0.14/$0.28 row.
- DeerFlowByteDance's open-source SuperAgent harness for long-horizon tasks. Orchestrates sub-agents, memory, sandboxes, and skills on LangGraph, with a browser-equipp.
- E2BFirecracker microVM sandboxes for AI agents. Hobby is $0 plus usage; Pro is $150/month. Open-source SDK on GitHub.
- Explee AutoGTMAutoGTM by Explee: a 24/7 AI sales agent that finds high-intent prospects, sends personalized outreach, handles replies, and books demos with pay-as-you-go p.
- FastClawLightweight AI Agent runtime and Multi-Agent Framework written in Go. An Agent Factory that creates, manages, and runs AI agents with personalities (SOUL.md).
- Grok BotSpaceXAI's always-on AI teammates that run on their own cloud computer, sign into your tools, and finish work end-to-end — available in beta for SuperGrok Heavy, Cursor Ultra, and Cursor Teams Premium subscribers.
- Hark HandoffComputer use agent that navigates any website end-to-end on a dedicated virtual computer. Book flights, order food, shop, and message candidates on LinkedIn.
- HeliconeOpen-source LLM gateway and traces. Cloud Free is $0. Pro is $79/month. Team is $799/month. Extra logs start at $0.28 per 100k.
- HerdrOpen-source runtime that keeps your coding agents alive: real terminal sessions on a background server, so Claude Code, Codex, and opencode keep working when.
- KitesurfCloudflare agent browser on Workers. GitHub 404. Not an open-source Chromium clone.
- LangfuseOpen-source LLM tracing and evals. Cloud Hobby is $0. Core is $29/seat. Pro is $199/seat. Plus usage after included units.
- LangGraphLangChain's low-level agent orchestration runtime: durable graphs, streaming, human-in-the-loop, and persistence. About 39,835 GitHub stars.
- LangSmithLangChain Cloud for traces, evals, and deploys. Plus is $39/seat. Startup is $1,400/month. LangSmith Engine is $2,000/month.
- LettaMemGPT's company and OSS agent memory runtime. GitHub letta-ai/letta is ~20.5k stars. Cloud is $20 and $200 per project plus usage.
- LuvusLuvus is Apache-2.0 Rust mission control that watches, resumes, and orchestrates coding agents in one TUI.
- MastraOpen-source TypeScript agent framework: agents, workflows, RAG, memory, MCP, and eval with a hosted platform. About 27,437 GitHub stars (2026-08-25).
- ModalPython serverless compute with a Sandbox API for untrusted agent code, scale-to-zero, and per-second CPU/GPU billing.
- Microsoft MXCMicrosoft Execution Containers: an open, cross-platform sandboxed code-execution system for running untrusted model output, plugins, and agent tools.
- nanobotUltra-lightweight, self-hosted personal AI agent framework in Python with WebUI, tools, long-term memory, MCP integrations, multi-agent workflows, and scheduled automation.
- OpenAI Agents SDKOpenAI's official Python and TypeScript agent runtime: agents, handoffs, guardrails, sessions, and tracing.
- OpenSquillaToken-efficient microkernel AI agent with ML-based smart routing, persistent memory, a layered sandbox, built-in search, and local embeddings. Apache 2.0.
- ShipAnyAgent-native AI SaaS template family: auth, payments, subscriptions, credit billing, i18n, storage, and AI generation pre-wired so coding agents can ship AI.
- SoL-PiSoL-Pi is NVIDIA's MIT Pi extension that cuts agent tokens with four opt-in mechanisms and no patch to Pi itself.
- SteelOpen-source browser API for agents. Cloud Launch is $0 plus usage with a one-time $30 credit. Scale is $250/month plus usage.
- TodosTask-driven workspace where a Chief agent splits your goal into todos, assigns each to agents by trade, and tracks progress — supporting 700+ models, including ChatGPT/Codex or GitHub Copilot sign-in without an API key.
- Trigger.devOpen-source durable execution platform for AI agents in TypeScript. Build long-running tasks and chat agents with no timeouts, checkpoint-based resume, retries, queues, and idempotency.
- Vast.aiGPU rental marketplace with interruptible and on-demand instances. Prices move by host. Confirm the live offer before you rent.
- NaturalAgent payments stack: accounts, cards, processing, billing, identity, observability, MCP.
- AnySearchPrivacy-first AI search infrastructure for agents: one API and MCP server unifying web and vertical-domain search with structured results that cut token waste.
- Context ModeAn MCP server and plugin that stops context-window bloat in AI coding agents, sandboxing MCP tool output into a searchable SQLite index and recovering it on demand.
- herdrmNative macOS console for herdr: see every coding agent across machines and jump into its live terminal.
- PlandexTerminal-based AI coding agent designed for large, multi-step tasks. Plans and executes across dozens of files with up to 2M tokens of context, MIT licensed.
- Spark-X2.5-4BXHToken's efficient 4B open-weight model: hybrid sliding-window attention for native 1M-token context, strong coding and agent performance, Apache 2.0, multilingual.
Items tagged with Agent Runtime (43)
Month Visit400000000DR: 88AS: 78
Month Visit50000000DR: 95AS: 95
Month Visit5000000DR: 95AS: 95
Month Visit5000000DR: 93AS: 95
Month Visit4000000DR: 95AS: 95
Month Visit4000000DR: 90AS: 92
Month Visit3000000DR: 92AS: 92
Month Visit3000000DR: 88AS: 90
Month Visit2000000DR: 93AS: 95
Month Visit1500000DR: 92AS: 94
Month Visit1500000DR: 90AS: 90
Month Visit1500000DR: 85AS: 87
Month Visit1500000DR: 80AS: 85
Month Visit1000000DR: 88AS: 88
Month Visit800000DR: 85AS: 85
Month Visit800000DR: 85AS: 85
Month Visit600000DR: 82AS: 82
Month Visit500000DR: 82AS: 80
Month Visit350000DR: 70AS: 72
Month Visit300000DR: 95AS: 95
Month Visit300000DR: 75AS: 78
Month Visit250000DR: 48AS: 52
