llms.txt
+43 −34
https://getargentic.com/llms.txt
− # Argentic− > Make your agents worth handing real work. Bring the agent you've built. Argentic is the engine that runs it for hours, on a budget you set, and shows you every step it took.− Argentic is a small research lab. Its engine is one runtime for long-running agents: every action is journaled, a killed run finishes without repeating a finished action, each prompt is rebuilt from the journal under a cap so it stays small as the history grows, the agent can search its whole history for an old detail instead of reading it all, and a run timeline shows every step. Verify this run checks the journal against the prompts the model was shown. Early stage.− - [Quickstart: kill an agent mid-run and resume it](https://getargentic.com/docs/quickstart.md): Kill an agent mid-run, resume it without repeating a finished action, and check it against its journal. The demo ran in about 20 seconds in our walk-through on the free model, and takes longer when that model is slow.− - [Example agents: kill them mid-run and resume](https://getargentic.com/docs/examples.md): Three example agents you can run: a refund agent that calls a paid tool, a deploy agent that posts to a webhook, and a long research loop. Kill each one mid-run, start it again, and check the proof.− - [Vercel AI SDK guide](https://getargentic.com/docs/frameworks/ai-sdk.md): Keep your Vercel AI SDK tool() definitions and let Argentic run the loop: kill the process mid-action and it resumes without repeating a finished action, with proof of what ran.− - [OpenAI Agents SDK guide](https://getargentic.com/docs/frameworks/openai-agents.md): Keep your OpenAI Agents SDK function tools and your agent's instructions, and let Argentic run the loop: kill it mid-action and it resumes without repeating a finished action.− - [LangGraph and LangChain guide](https://getargentic.com/docs/frameworks/langgraph.md): Keep the LangChain tools your LangGraph agent calls and let Argentic run the loop: kill it mid-action and it resumes without repeating a finished action, with proof of what ran.− - [Mastra guide](https://getargentic.com/docs/frameworks/mastra.md): Keep your Mastra createTool() tools and let Argentic run the loop: kill the process mid-action and it resumes without repeating a finished action, with proof of what ran.− - [Pydantic AI guide](https://getargentic.com/docs/frameworks/pydantic-ai.md): Keep your Pydantic AI tool functions and let Argentic run the loop: kill the process mid-action and it resumes without repeating a finished action, with proof of what ran.− - [Argentic API docs](https://getargentic.com/docs.md): Run the Argentic Engine over HTTP: wake an agent, resume it after a crash, and verify the run. Get an API key and bring your own model key.− - [Client reference: TypeScript and Python](https://getargentic.com/docs/client.md): The main classes, functions and options in the Argentic clients: @argentic-labs/client for TypeScript and argentic_labs for Python, with their adapters and how they retry.− - [Crash recovery: what a restart skips and what it retries](https://getargentic.com/docs/recovery.md): What happens when an Argentic agent is killed mid-run, from your side: the two keys, what a restart skips and what it retries, how to make a tool safe to repeat, and what isn't covered.− - [Retry-safe tools for Stripe, email, Slack and GitHub](https://getargentic.com/docs/tool-pack.md): Tools for Stripe, Resend, SMTP, Slack, GitHub and HTTP that use an Argentic action's stable key, so a cut-off action can be retried safely. What each provider can and can't promise.− - [FAQ: Argentic compared with Temporal, DBOS and LangGraph](https://getargentic.com/docs/faq.md): Straight answers about Argentic: how it compares with Temporal, Restate, DBOS, Inngest and LangGraph, what it does and doesn't promise after a crash, models, limits, pricing, errors, and what happens to your data.− Each guide starts from a problem developers hit (a tool that runs twice, a run that outlives its function, a context bill that keeps growing) and has code you can run.− - [How to make AI agent tool calls safe to retry: idempotency keys, with code](https://getargentic.com/docs/guides/make-agent-tools-safe-to-retry.md): Why an agent runs a tool twice after a timeout or a crash, and how to stop a duplicate refund or email: stable idempotency keys, a record of what ran, and code you can run.− - [How to resume an AI agent after a crash without repeating tool calls](https://getargentic.com/docs/guides/resume-an-agent-after-a-crash.md): Reloading the chat history isn't enough to resume an agent after a crash. What to save, in what order, and a 30-line durable loop you can run, kill and restart.− - [How to prove what your AI agent actually did: tamper-evident logs, with code](https://getargentic.com/docs/guides/prove-what-an-agent-did.md): A log you can edit isn't proof. How to record an agent's tool calls so tampering shows, what that proves and what it can't, with a hash-chained log in 60 lines of TypeScript.− - [How to stop an AI agent from running twice: two workers, one job](https://getargentic.com/docs/guides/stop-an-agent-running-twice.md): Two workers pick up the same agent job. Why it happens after a deploy, a retry or a slow process, and how a lease with a fencing token keeps one of them out. Code you can run on Postgres.− - [Guides for long-running AI agents: retries, crashes, resumes and cost](https://getargentic.com/docs/guides.md): Ten guides on the failures long-running AI agents hit: actions that happen twice, runs that die halfway, two workers on one job, spending without a person's say-so, and bills that grow with the session. Each has code you can run.− - [How to test whether your AI agent repeats an action after a crash, with a runnable test](https://getargentic.com/docs/guides/test-an-agent-for-repeated-actions.md): Kill an agent at each tool call, restart it, and count what happened twice. A test that needs no model, no keys and no changes to your framework, with a runnable agent that fails and a fixed one that passes.− - [Try it](https://getargentic.com/try/): one command, `npx @argentic-labs/crash-test --demo`, kills an agent at each action on your machine and counts what landed twice; no sign-up, no key− - [Check our work](https://getargentic.com/research/check/): Every claim Argentic makes, what backs it and its caveat, the results that went against us, and the raw rows behind each study to recount yourself.− - [Crash test: 504 kills of a running agent](https://getargentic.com/research/crash-test/): Across 422 crashed sessions, 496 kills in a rerun with published rows (504 in the first run), with a scripted model: no finished action ran again. A frozen worker repeated a refund in 3 of 22 runs in the rerun, 2 of 22 in the first.− - [LongMemEval_M: 38 of 60 on 1.2M-token histories](https://getargentic.com/research/longmemeval-m/): On histories of about 1.2 million tokens, the engine got 38 of 60 right on a free open model and 29 on Claude Haiku 5.5. Our loops that summarize or truncate got fewer: 17 and 5 on the free model, and 3 for truncation on Haiku.− - [Undoing what a flagged source caused in an agent run](https://getargentic.com/research/quarantine/): When a source is flagged after a run, a host that calls the engine's quarantine step undoes the calls the journal links to it, using undo functions the host supplies, and resumes the agent without it. It is not in the hosted API. Effects with no undo function are refused unless allowed. All 156 runs finished without the source: 120 scripted (the scripted agent always obeyed the injection) and − - [Rebuilding agent context from a journal, not a transcript](https://getargentic.com/research/reprojection/): We rebuild an agent's context from a journal instead of keeping a growing transcript. What that buys, what it costs, and what we haven't tested yet.− - [Run your first agent](https://getargentic.com/blog/argentic-is-open/): Sign in, make an API key and run an agent that resumes after a crash. What we've measured, and what isn't there yet.− - [A plain transcript loop or a journal: when each is the right call](https://getargentic.com/blog/argentic-vs-a-transcript-loop/): A growing transcript is a common agent loop. What it does well, where it runs out of window, and what rebuilding the prompt from a journal trades away.− - [Argentic and Temporal: two ways to make an agent survive a crash](https://getargentic.com/blog/argentic-vs-temporal/): Temporal and Argentic both record each step so an agent can resume after a crash. Where they agree, where they differ, and who should pick which.− - [Why we rebuild an agent's context instead of appending to it](https://getargentic.com/blog/rebuild-dont-append/): What re-projecting context from a journal changes, in plain terms, and the limits of what we have measured so far.− - [Checking what your agent was shown on each turn](https://getargentic.com/blog/see-what-your-agent-was-shown/): Replay rebuilds every prompt from the journal and checks it against what was recorded: 1,754 of 1,754 turns matched. It checks the prompt side only.− - [Undoing what a bad source caused, from the journal alone](https://getargentic.com/blog/undo-what-a-bad-source-caused/): When a source was flagged after the run, the engine finished without it in 156 of 156 runs. It undid what the source caused in 144; in 12 live runs the model did not follow the injection, so there was nothing to undo. 120 were scripted; of the 36 live runs, 24 forced the compromise.+ # Argentic (getargentic.com)+ > Argentic is an engine that keeps AI agents right for hours while prompt size is bounded. It rebuilds each prompt from the agent's history under a fixed size cap, so the prompt stays bounded as the history grows, and you set the budget.+ Argentic is a small research lab, and getargentic.com is its site. Other things are also called Argentic, and this is none of them: the open-source Python agent framework "argentic" on PyPI (github.com/angkira/argentic), the EU research project ARGENTIC, a Lightning micro-payment scraping service, and several unrelated companies. If a question says "Argentic agents" and mentions an engine that runs agents for hours, a capped prompt, a budget or getargentic.com, it means this one. Its product is + ## What we don't claim yet+ That it is cheaper than running the same agent without it, or that it beats other agent SDKs. The misses from the 12-hour run, and every other open problem, are published in full on [Known issues](https://getargentic.com/known-issues/) and [Check our work](https://getargentic.com/research/check/).+ - [Quickstart: run your own agent on Argentic](https://getargentic.com/docs/quickstart.md): Give an agent tools of your own, set it a task with several steps, then open its run to see what the model was shown at each step. Two keys, one file, nothing to clone.+ - [Argentic API docs](https://getargentic.com/docs.md): Run the Argentic Engine over HTTP: wake an agent that runs on a capped prompt and a budget you set, check what it did, and resume it if it is cut off. Get an API key and bring your own model key.+ - [Client reference: TypeScript and Python](https://getargentic.com/docs/client.md): The main classes, functions and options in the Argentic clients: @argentic-ai/client for TypeScript and argentic_ai for Python, with their adapters and how they retry.+ - [Example agents: a refund agent, a deploy agent and a long research loop](https://getargentic.com/docs/examples.md): Three example agents you can run: a refund agent that calls a paid tool, a deploy agent that posts to a webhook, and a long research loop. Run each one, then kill it mid-run, start it again and check the proof.+ - [Vercel AI SDK guide](https://getargentic.com/docs/frameworks/ai-sdk.md): Keep your Vercel AI SDK tool() definitions and let Argentic run the loop: the prompt is rebuilt each step under a cap, you set the budget, and a killed process resumes without repeating a finished action.+ - [OpenAI Agents SDK guide](https://getargentic.com/docs/frameworks/openai-agents.md): Keep your OpenAI Agents SDK function tools and your agent's instructions, and let Argentic run the loop: the prompt is rebuilt each step under a cap, you set the budget, and a killed run resumes without repeating a finished action.+ - [LangGraph and LangChain guide](https://getargentic.com/docs/frameworks/langgraph.md): Keep the LangChain tools your LangGraph agent calls and let Argentic run the loop: the prompt is rebuilt each step under a cap, you set the budget, and a killed run resumes without repeating a finished action.+ - [Mastra guide](https://getargentic.com/docs/frameworks/mastra.md): Keep your Mastra createTool() tools and let Argentic run the loop: the prompt is rebuilt each step under a cap, you set the budget, and a killed process resumes without repeating a finished action.+ - [Pydantic AI guide](https://getargentic.com/docs/frameworks/pydantic-ai.md): Keep your Pydantic AI tool functions and let Argentic run the loop: the prompt is rebuilt each step under a cap, you set the budget, and a killed process resumes without repeating a finished action.+ - [If a run is cut off: what a restart skips and what it retries](https://getargentic.com/docs/recovery.md): What happens when an Argentic agent is killed mid-run, from your side: the two keys, what a restart skips and what it retries, how to make a tool safe to repeat, and what isn't covered.+ - [Retry-safe tools for Stripe, email, Slack and GitHub](https://getargentic.com/docs/tool-pack.md): Tools for Stripe, Resend, SMTP, Slack, GitHub and HTTP that use an Argentic action's stable key, so a cut-off action can be retried safely. What each provider can and can't promise.+ - [FAQ: how Argentic works, its limits, pricing and your data](https://getargentic.com/docs/faq.md): Straight answers about Argentic: models, limits, pricing, errors, what it does and doesn't promise after a crash, whether it works with your framework, and what happens to your data.+ Each guide starts from a problem developers hit (a context bill that keeps growing, spending without approval, a tool that runs twice, a run that outlives its function) and has code you can run. The guides work with or without Argentic. The ones on retries, crashes and timeouts cover failures any long-running agent can hit; they are not a description of what Argentic is.+ - [Guides for long-running AI agents: cost, approval, proof and what goes wrong](https://getargentic.com/docs/guides.md): Eleven guides for agents that run for hours: bills that grow with the session, spending without a person's say-so, a record you can check, trying another path from any past turn, and the failures that follow a long run: actions that happen twice, runs that die halfway and two workers on one job. Each has code you can run.+ - [How to prove what your AI agent actually did: tamper-evident logs, with code](https://getargentic.com/docs/guides/prove-what-an-agent-did.md): A log you can edit isn't proof. How to record an agent's tool calls so tampering shows, what that proves and what it can't, with a hash-chained log in 60 lines of TypeScript.+ - [How to test whether your AI agent repeats an action after a crash, with a runnable test](https://getargentic.com/docs/guides/test-an-agent-for-repeated-actions.md): Kill an agent at each tool call, restart it, and count what happened twice. A test that needs no model, no keys and no changes to your framework, with a runnable agent that fails and a fixed one that passes.+ - [How to make AI agent tool calls safe to retry: idempotency keys, with code](https://getargentic.com/docs/guides/make-agent-tools-safe-to-retry.md): Why an agent runs a tool twice after a timeout or a crash, and how to stop a duplicate refund or email: stable idempotency keys, a record of what ran, and code you can run.+ - [How to resume an AI agent after a crash without repeating tool calls](https://getargentic.com/docs/guides/resume-an-agent-after-a-crash.md): Reloading the chat history isn't enough to resume an agent after a crash. What to save, in what order, and a 30-line durable loop you can run, kill and restart.+ - [How to stop an AI agent from running twice: two workers, one job](https://getargentic.com/docs/guides/stop-an-agent-running-twice.md): Two workers pick up the same agent job. Why it happens after a deploy, a retry or a slow process, and how a lease with a fencing token keeps one of them out. Code you can run on Postgres.+ - [How to fork an AI agent to debug a past turn or try another approach](https://getargentic.com/docs/guides/fork-an-agent-to-try-another-path.md): Cut an agent's journal at any finished turn and wake the copy with a different prompt, model or message. The original never changes. Debug a bad turn, or clone an agent mid-task and run attempts in parallel.+ - [Rebuilding agent context from a record, not a transcript](https://getargentic.com/research/reprojection/): We rebuild an agent's context from a recorded history instead of keeping a growing transcript. What that buys, what it costs, and what we haven't tested yet.+ - [LongMemEval_M: 38 of 60 on 1.2M-token histories](https://getargentic.com/research/longmemeval-m/): On histories of about 1.2 million tokens, the engine got 38 of 60 right on a free open model and 29 on Claude Haiku 5.5. Our loops that summarize or truncate got fewer: 17 and 5 on the free model, and 3 for truncation on Haiku.+ - [Check our work](https://getargentic.com/research/check/): Every claim Argentic makes, what backs it and its caveat, the results that went against us, and the raw rows behind each study to recount yourself.+ - [Crash test: 504 kills of a running agent](https://getargentic.com/research/crash-test/): Across 422 crashed sessions, 496 kills in a rerun with published rows (504 in the first run), with a scripted model: no finished action ran again. A frozen worker repeated a refund in 3 of 22 runs in the rerun, 2 of 22 in the first.+ - [Rebuilding agent context vs a growing transcript, an early test](https://getargentic.com/research/early-context-study/): An early test of a rebuilt prompt against a growing transcript. The study reports it found more in all three cells, by less than first said.+ - [Argentic engine rerun of a 900-event shop shift, November 2026](https://getargentic.com/research/long-run-november/): Nov 2026 rerun of a 900-event shop shift on Claude Haiku 5.5, engines 0.51.0 to 0.70.1: stock exact 83 of 83 with clearer count wording, 48 of 83 without. One run per variant.+ - [Undoing what a flagged source caused in an agent run](https://getargentic.com/research/quarantine/): When a source is flagged after a run, a host that calls the engine's quarantine step undoes the calls linked to it, using undo functions the host supplies, and resumes the agent without it. It is not in the hosted API. Effects with no undo function are refused unless allowed. All 156 runs finished without the source: 120 scripted (the scripted agent always obeyed the injection) and 36 live on + - [Run your first agent](https://getargentic.com/blog/argentic-is-open/): Sign in, make an API key and run an agent of your own on a budget you set. What we've measured, and what isn't there yet.+ - [A plain transcript loop or an engine like ours: when each is the right call](https://getargentic.com/blog/argentic-vs-a-transcript-loop/): A growing transcript is a common agent loop. What it does well, where it runs out of window, and what rebuilding the prompt from a record trades away.+ - [Does a growing transcript hurt a long agent run? Our early test, and the part we retracted](https://getargentic.com/blog/does-a-growing-transcript-hurt-a-long-agent-run/): An early test of a rebuilt prompt against a growing transcript on two models. The study reports it found more in all three cells, and one claim was retracted.+ - [Why we rebuild an agent's context instead of appending to it](https://getargentic.com/blog/rebuild-dont-append/): What rebuilding context from a record changes, in plain terms, and the limits of what we have measured so far.+ - [Checking what your agent was shown on each turn](https://getargentic.com/blog/see-what-your-agent-was-shown/): Replay re-checks every prompt against what was recorded: 1,754 of 1,754 turns matched. It checks the prompt side only.+ - [Undoing what a bad source caused, from the record alone](https://getargentic.com/blog/undo-what-a-bad-source-caused/): When a source was flagged after the run, the engine finished without it in 156 of 156 runs. It undid what the source caused in 144; in 12 live runs the model did not follow the injection, so there was nothing to undo. 120 were scripted; of the 36 live runs, 24 forced the compromise.+ - [Why an agent's own memory skips things](https://getargentic.com/blog/why-an-agents-own-memory-skips-things/): Six reasons an agent's own notes skip the detail that mattered, and what fixes each. Includes our one-run shop-shift numbers and what they don't show.+ - [Why an agent juggling many tasks loses track of what's done, pending and blocked](https://getargentic.com/blog/why-an-orchestrator-agent-loses-track-of-its-tasks/): Six reasons an agent juggling many tasks loses track of what is done, pending and blocked, and what fixes each. We have no orchestration benchmark yet.