# ReadyAgents > Concatenated markdown of the public product pages (home, docs, why-readyagents, waitlist). Current core: 2.0.6. Packs are waitlisted and not for sale. ## Home # Agent workflows that stay reliable. Free, self-hosted, Apache-2.0. One-shot agent workflows with an MCP toolkit — pip install readyagentsdev (Current 2.0.6), or clone; bring your own keys. ReadyAgents is a free, self-hosted Apache-2.0 local one-shot agent workflow engine plus MCP toolkit: pip install readyagentsdev (Current 2.0.6), bring your own keys; always-on packs are waitlisted and not for sale. - [Install from PyPI](https://pypi.org/project/readyagentsdev/) - [Join the waitlist](/waitlist) - [View on GitHub →](https://github.com/readyagentsdev/readyagents-core) - Free local core - BYOK ## First run No keys for that run. ``` pip install readyagentsdev readyagents new f --from-example calc_pipeline readyagents run f/workflow.yaml ``` Current **2.0.6**. Or clone https://github.com/readyagentsdev/readyagents-core, `pip install -e .`, then `readyagents run examples/calc_pipeline.yaml`. [Release notes](https://github.com/readyagentsdev/readyagents-core/releases/tag/v2.0.6). Packs waitlisted, not for sale. ## What is ReadyAgents? ReadyAgents is an open-core product. The core Agent Workflow and MCP Toolkit is free and open source. The core is the free local toolkit. ### Open-source core Agent Workflow + MCP Toolkit on GitHub. Inspect it, fork it, run it with your own keys. ### Bring your own keys Bring your own keys. You keep the provider account and the bill. ## What is in core through 2.0.6 Short facts for humans and agents. Local, BYOK, no hosted control plane. Packs stay waitlisted and not for sale. ### Local YAML/JSON workflows One-shot local runs from YAML or JSON. Bring your own provider keys. Persist and resume after each node. ### MCP toolkit (stdio) `readyagents mcp serve` defaults to stdio so existing MCP hosts keep working unchanged. ### Streamable HTTP + tasks Opt-in loopback Streamable HTTP with MCP 2026-07-28 task handles (start/poll/decide/cancel). No hosted recovery. ### Browser approval / HITL Localhost approval UI and signed decisions for human-in-the-loop gates — same audit path as the CLI. ### SQLite migrate path Readable JSON run records by default; `readyagents runs migrate` copies into an opt-in local SQLite store. ### Sandboxed builtins Workspace-bound tools such as `calc`, file read/write, and `list_dir`. No pack marketplace and no always-on hosted agents in core. ## How it works ### 01. Start with the open toolkit Current 2.0.6: `pip install readyagentsdev`, then `readyagents new f --from-example calc_pipeline` and `readyagents run f/workflow.yaml`. No keys for that run. Or clone [github.com/readyagentsdev/readyagents-core](https://github.com/readyagentsdev/readyagents-core) and run examples/calc_pipeline.yaml. ### 02. Compose a reliable workflow Write a YAML (or JSON) workflow. HITL is [`docs/first-ten-minutes.md`](https://github.com/readyagentsdev/readyagents-core/blob/main/docs/first-ten-minutes.md). ### 03. If you need always-on later If you need always-on later, join the waitlist. ## Want always-on agents? Join the waitlist. Packs are not for sale yet. The free core stays a local one-shot. [Join the waitlist](/waitlist) ## Get started The open-source toolkit is the starting point. Packs are not for sale. - [Read the getting started guide](/docs) - [GitHub](https://github.com/readyagentsdev/readyagents-core) 1. **Install from PyPI** — pip install readyagentsdev (Current 2.0.6, Python 3.11+) 1. **Materialize the keyless example** — readyagents new f --from-example calc_pipeline 1. **Run it** — readyagents run f/workflow.yaml — no API keys needed. 1. **Or clone instead** — git clone https://github.com/readyagentsdev/readyagents-core.git && cd readyagents-core && python -m venv .venv && source .venv/bin/activate && pip install -e . && readyagents run examples/calc_pipeline.yaml 1. **Add keys only if you want LLM examples** — Copy .env.example to .env and set your own provider key. The first run above works without this. Tried it? Open an [I-ran-this issue](https://github.com/readyagentsdev/readyagents-core/issues/new?template=i-ran-this.md). We are not launching. ## Join the waitlist for always-on packs Packs are not for sale yet. Open Core stays a free local one-shot, BYOK. One email when that changes. - One email when packs exist - Open Core stays free, local, BYOK POST `/waitlist` with `email` (required work email), optional `name`, and `interest` (`toolkit` | `premium` | `both`). ## Getting started # Get started The open-source toolkit is the starting point. Packs are not for sale. ``` pip install readyagentsdev readyagents new f --from-example calc_pipeline readyagents run f/workflow.yaml ``` Python 3.11+. No API keys needed for that first run. Current **2.0.6**. Or clone and `pip install -e .`, then `readyagents run examples/calc_pipeline.yaml`. The wheel ships `examples/`. Current core: [readyagentsdev 2.0.6](https://github.com/readyagentsdev/readyagents-core/releases/tag/v2.0.6). Packs waitlisted, not for sale. Install from the [MCP Registry](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.readyagentsdev/readyagents) as `io.github.readyagentsdev/readyagents`. Tried it? Open an [I-ran-this issue](https://github.com/readyagentsdev/readyagents-core/issues/new?template=i-ran-this.md). We are not launching. - [View on GitHub](https://github.com/readyagentsdev/readyagents-core) - [Join the waitlist](/waitlist) ## 01. Install from PyPI pip install readyagentsdev (Current 2.0.6, Python 3.11+) ## 02. Materialize the keyless example readyagents new f --from-example calc_pipeline ## 03. Run it readyagents run f/workflow.yaml — no API keys needed. ## 04. Or clone instead git clone https://github.com/readyagentsdev/readyagents-core.git && cd readyagents-core && python -m venv .venv && source .venv/bin/activate && pip install -e . && readyagents run examples/calc_pipeline.yaml ## 05. Add keys only if you want LLM examples Copy .env.example to .env and set your own provider key. The first run above works without this. ## What’s in the core Local one-shot runs. Not always-on. These are in readyagentsdev 2.0.6: local YAML/JSON workflows with persist/resume (BYOK), the MCP toolkit over stdio by default, opt-in loopback Streamable HTTP with MCP task handles, localhost browser approval, JSON run records with `readyagents runs migrate` to SQLite, and sandboxed builtins. - Approval (HITL) — a run can pause for approve or reject, then resume - Persist + resume — state is written after each node; continue from the last success - Fan-out — `parallel` branches - Include — run another workflow file - `foreach` — bounded sequential loop over a list - Agent `tools:` — allowlisted tool-use loop - Include / parallel resume — successful children are not re-run - MCP toolkit — `readyagents mcp serve` defaults to stdio - Opt-in loopback Streamable HTTP + MCP task handles (start/poll/decide/cancel) - Localhost browser approval — signed decisions, same audit path as the CLI - JSON run records + `readyagents runs migrate` to SQLite - `--dry-run` does not write files - File tools default to the workflow directory (`READYAGENTS_WORKSPACE` still wins) - Successful runs print `run_id:` - Structured JSON logs — `--log-format json` - Per-node token/cost tracking and budget limits - External decisions — `readyagents decide` / `--decision-file` (no always-on listener) - Append-only audit trail under `$READYAGENTS_HOME/audit/` - `list_dir` — sandboxed directory listing - `readyagents eval` — local fixture suites, no network Try `examples/approval_gate.yaml`, `examples/foreach_calc.yaml`, `examples/agent_tools.yaml`, `examples/multi_gate.yaml`, `examples/eval/pass.yaml`, `examples/list_dir.yaml`, and `examples/connector_demo.yaml`. `--json` prints machine-readable output on `run`, `resume`, `validate`, `eval`, `packs`, and `runs show`. `--log-level` is `DEBUG` / `INFO` / `WARNING` / `ERROR`. Install with `pip install readyagentsdev`, or clone and `pip install -e .`. The wheel ships `examples/`; pip-only first run can use `readyagents new NAME --from-example` or `readyagents new`. ## [Why ReadyAgents?](/why-readyagents) Where MCP connectivity stops and durable orchestration begins, with honest verdicts for ReadyAgents 2.0.6. ## Bring your own API keys ReadyAgents is designed so you keep provider accounts and spend. Core-only BYOK. Packs waitlisted, not for sale. Use the key you have. ## Want always-on agents? When a workflow has to stay up, join the waitlist. Packs are not for sale. [Join the waitlist](/waitlist) ## Why ReadyAgents # Why ReadyAgents? MCP connectivity is not durable orchestration. This page records two public reports about gaps between MCP wiring and durable workflow execution, plus one design note about how modern MCP asks a question. It states plainly what ReadyAgents 2.0.6 does and does not do. Each verdict is about our own software only. Why not LangGraph HITL / n8n MCP as a hosted control plane? Use those hosted surfaces when you need always-on recovery; ReadyAgents 2.0.6 is local persist/resume (approval pause = exit 2, then `readyagents resume … --approve`) and only PARTIAL on hosted recovery. If you are evaluating a LangGraph or n8n MCP surface for durable HITL, this page is the honest comparison: ReadyAgents 2.0.6 is a self-hosted alternative when you need local persist/resume, and it is still only PARTIAL on hosted recovery. | Capability | ReadyAgents 2.0.6 | LangGraph MCP | n8n MCP Trigger | |---|---|---|---| | Stateful MCP-exposed runs | Partial | No | No | | HITL on the MCP trigger surface | Partial | No | No | | Retry-shaped elicitation (MRTR) | No | — | — | | Self-hosted / BYOK | Yes | Yes | Yes | ## LangGraph MCP surface: MCP-exposed runs remain stateless Sources (as of 15 September 2026): [langchain-ai/langgraph issue 8725](https://github.com/langchain-ai/langgraph/issues/8725) and [LangSmith server MCP docs](https://docs.langchain.com/langsmith/server-mcp) Quote issue 8725: > When a LangGraph Platform deployment is exposed as an MCP server, every tool call is executed as a temporary run: no durable state exists even while it runs (`checkpointer=None`), and its auto-created thread is deleted on completion. Quote LangSmith docs: > The current LangGraph MCP implementation does not support sessions. Each `/mcp` request is stateless and independent. **ReadyAgents 2.0.6: PARTIAL.** We persist local workflow state and support resume/approval pauses. Opt-in loopback Streamable HTTP implements MCP 2026-07-28 tasks (start/poll/decide/cancel), but there is still no hosted recovery surface. This comparison is about the MCP surface, not LangGraph's other surfaces. ## n8n MCP Server Trigger: a long synchronous call can lose the result, and HITL is unsupported Sources (as of 15 September 2026; thread dated 2026-08-25): [n8n community thread on MCP Server Trigger 502 after ~125s](https://community.n8n.io/t/mcp-server-trigger-returns-502-after-125s-while-long-running-subworkflow-completes-successfully-and-is-triggered-twice/309413) and [n8n MCP Server tools reference](https://docs.n8n.io/connect/connect-to-n8n-mcp-server/mcp-server-tools-reference/) Quote the 2026-08-25 thread: > MCP request starts → long-running subworkflow continues → MCP request/connection times out after about 120 seconds → external caller receives 502 → n8n subworkflow continues and eventually succeeds Quote the reply: > A tool that legitimately runs 2 to 4 minutes cannot answer synchronously. Quote the current MCP tools reference: > Executing workflows with multi-step forms or any kind of human-in-the-loop interactions isn't supported. **ReadyAgents 2.0.6: PARTIAL.** We checkpoint locally and have an approval node. Loopback MCP tasks (and deprecated `/runs`) exist for explicitly started HTTP, but that is not a networked public MCP Server Trigger, so we still do not solve the networked MCP Server Trigger case end-to-end. n8n's instance-level `execute_workflow` already returns an execution ID immediately; this page is only about the MCP Server Trigger surface. ## Design note: modern MCP uses retry-shaped multi-round trips Sources (as of 15 September 2026; spec dated 2026-07-28): [MCP specification: Multi Round-Trip Requests (MRTR)](https://modelcontextprotocol.io/specification/2026-07-28/basic/patterns/mrtr) and [Python SDK elicitation handlers](https://py.sdk.modelcontextprotocol.io/handlers/elicitation/) Quote the spec: > Multi Round-Trip Requests (MRTR) was introduced in this version of the MCP specification. This replaces the previous approach of sending server-initiated requests. Quote the Python SDK: > A resolver works on every connection. For a client on a legacy connection the SDK sends it the question directly; on a 2026-07-28 connection the SDK returns the question from the call, and the client's next attempt carries the answer. This is a design note, not a competitor gap. The ask is now a stateless retry-shaped resolver; ReadyAgents sidesteps it with a persisted approval node, and does not implement MRTR or protocol elicitation. ## Waitlist # Join the waitlist for always-on packs Packs are not for sale yet. Open Core stays a free local one-shot, BYOK. One email when that changes. Open Core is free now. Always-on packs are not for sale. Leave a work email if you want one note when that changes. Nothing else. - One email when packs exist - Open Core stays free, local, BYOK ## Form POST `/waitlist` - `email` (required) — work email you check. We do not sell or share this list. - `name` (optional) - `interest` — `toolkit` (free core), `premium` (always-on packs), or `both` Joining the waitlist does not create a paid contract. Packs are not for sale.