Recursion Managed Agents
Managed agents for engineering and research teams: runs fleets of agents on a team's code, infrastructure, experiments and evals, with every run graded and remembered.
Find alternatives to Recursion Managed Agents
What it does
- Model training
- Model inference
- Evaluation and observability
- Agent orchestration
- Workflow automation
Used for
- Agentic coding
- Financial analysis
Features 11
- Autonomous long-running sessionsAgents start on failing builds, alerts, merged PRs, schedules or API calls and run for days or weeks.
- Multi-agent coordinationA coordinator plans the work and spawns specialists in parallel.
- Graded outcomesA separate grader checks each session against your rubric until every criterion passes.
- 100+ integrationsWorks across code, CI, incidents, data and docs, limited to the tools you allow.
- VaultsA named group of credentials for agents to use.
- AutomationsStart agent sessions on a schedule, on a Slack, GitHub or webhook event, or by hand.
- AdvisorAnswers questions the agent asks while it works.
- Referenced sessionsAn earlier session that a new or running session may read.
- EnvironmentsThe saved definition of a session sandbox: compute size, workspace disk, setup script and network access.
- Enterprise SSOLets people at your company sign in to Recursion through your own identity provider.
- Fleet viewShows every agent at work in one place.
Sources
- Pricing
-
Official documentation · 5 Sep 2026
Fetched. No pricing tiers, rates or figures anywhere on the page; contact-sales only.
- Description
-
Official documentation · 18 Oct 2026
"Managed agents for engineering and research teams. Recursion Managed Agents runs fleets of agents on your code, infrastructure, experiments and evals, and every run is graded and remembered."
- Used for
-
Official documentation · 24 Oct 2026
'Red builds, flaky tests, dependency bumps, an eval rerun on every checkpoint, a sweep that needs watching overnight.' (https://labelbox.com/products/recursion/) / 'Rebuilds the revenue forecast from pipeline, usage and bookings.' (https://labelbox.com/products/recursion/)
- Sold within
-
Official documentation · 15 Sep 2026
Live re-check 2026-09-15: own dedicated product page ("Recursion is the managed agent platform for enterprise work"), only a related, not parent-required, mention of Horizon.
- Name
-
Official documentation · 18 Oct 2026
Page title "Recursion Managed Agents | Labelbox".
- Interfaces
-
Platform listing · 14 Oct 2026
npm listings published by Labelbox (npm scope @labelbox, maintainer labelbox-operator): '
recursion— the Recursion CLI' / 'The Recursion TypeScript SDK, generated from the backend OpenAPI spec'. - Modalities
-
Official documentation · 20 Oct 2026
Product page: Hand them a goal, not a script: fix this regression, find the fastest config, keep every dependency current. … Delivers: A tested pull request with a preview link, ready for review … Delivers: A postmortem draft in Confluence, every event linked to its source
- Intended for
-
Page copy references 'real enterprise execution' and 'enterprise software stack' for developing enterprise specialist agents.
Also from Labelbox
-
Horizon Platform
Horizon supplies RL training gyms and evaluations for reasoning, tool use and computer use, using WorldSim to simulate enterprise environments such as GitLab, Jira, CRM, email and chat and to produce calibrated reward and preference signals for post-training.
-
Terra Data service
Terra is Labelbox's robotics data product delivering video, trajectories and multimodal annotations across pre-training, post-training and evaluation stages, including expert teleoperation with action labels and multiple camera perspectives for embodied foundation models.
-
Alignerr Data service
Alignerr is Labelbox's expert-network product that routes AI training and evaluation tasks to credentialed contributors across 200+ knowledge domains and 40+ countries and returns structured outputs for RL training, RLHF and evaluation workflows.
-
Catalog Application
Catalog is Labelbox's data curation and search product providing out-of-the-box search across images, text, video, conversations and documents over metadata, vector embeddings and annotations without building your own vector database infrastructure.
-
Annotate Application
Annotate is the data labeling product within Labelbox, providing 10+ built-in editors for multimodal chat, LLM evaluation, prompt/response generation, computer vision and NLP, plus customizable labeling and review workflows and team performance monitoring.
-
Labelbox Foundry Developer tool
Foundry runs third-party foundation models over data already in Labelbox to pre-label and enrich image, text and document datasets without code, routing the predictions to human review; billed as inference cost per model run plus Labelbox Units.
Open Labelbox in the directory
Something wrong here? Send a correction — quote this product id: labelbox-recursion.