Get This Tool
Autonomy
Summary
Most autonomous agent frameworks let an agent run until it does something irreversible — file deleted, API called, commit pushed — with no gate between planning and execution. Autonomy is built around the opposite assumption: every tool call passes through a risk-classified approval layer before it fires.
The core loop — AgentLoop — runs up to a configured step ceiling, selects from 15 bundled procedural skills, ranks candidate actions across five weighted dimensions using beam search, executes through ActionGateway with LOW/MEDIUM/HIGH risk labels, then evaluates and learns. Every event in that chain is stored via event sourcing, so the full run is replayable. The learning loop drafts new skills after a successful run and queues them for review rather than auto-applying them. The wall appears when you need agents running in parallel or sharing state across concurrent sessions — the architecture is single-loop, single-goal. Teams that outgrow that model start wiring external orchestration around it.
Bottom line: Pick this for a single-agent codebase debugging or systematic debugging workflow where you need a full audit trail; plan a different architecture when your use case demands parallel agents or multi-goal coordination the single AgentLoop cannot express.
Pricing Plans
Usage-BasedLast verified 1 week ago- Price
- $75/mo
- Free Tier
- $25 credit over first 7 days
Free trial
When you sign up, we give you $25 of credit to use over your first 7 days
- $25 credit
- 7 day duration
Base bundle
Base bundle includes 1 Seat license, 744 Regular compute container hours, 100 GBs of data transfer, and 1 GB of storage
- 1 Seat license
- 744 Regular compute container hours
- 100 GBs of data transfer
- 1 GB of storage
u00c0 la carte items
Pay only for consumption of underlying infrastructure beyond the Base bundle
- Regular compute: $25/month per container
- Big compute: $250/month per container
- Public Endpoints: $0.10/GB
- Private Links: $10/month per service plus $0.10/GB
- Storage: $1/GB/month
- Seat Licenses: $25/person/month
- Inference Models pricing varies by model
View full pricing on autonomy-landing-page.vercel.app →
Pricing may have changed since last verified. Check the official site for current plans.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- ActionGateway classifies every tool call as LOW, MEDIUM, or HIGH risk and routes it through an ApprovalPolicy before execution, so you get a stop point before an agent overwrites a file or calls an external API in an unreviewed context.
- Full event-sourcing audit trail from run_started through run_finished, which means a failed or unexpected run can be replayed step-by-step rather than reconstructed from logs after the fact.
- LearningLoop drafts new ProcedureSkills after successful runs and queues them for human review rather than auto-merging, so the agent's skill library grows without accumulating unreviewed automation.
- RecipeEngine promotes repeated successful action patterns to reusable recipes after two confirmed successes, so the LLM is not re-reasoning from scratch on tasks the agent has already solved before.
- Provider-agnostic LLM configuration across nine endpoints including local Ollama, so switching from a cloud provider to a local model for cost or privacy reasons is a config change rather than a code change.
Cons
Sign in to edit- The AgentLoop is a single-goal, single-thread loop with a hard step ceiling (default max_steps=12). Tasks that require parallel subtasks or concurrent agent coordination have no native path — teams that need multi-agent parallelism add an external orchestration layer, which means maintaining two systems.
- The skill library and RecipeEngine improve through accumulated runs, but on first deployment against a novel domain, the agent has no relevant skills or recipes yet and falls back entirely on LLM proposals. Teams handling narrow, high-specificity domains report writing custom ProcedureSkills before production use.
- Browser tooling depends on Playwright headless Chromium and is opt-in with MEDIUM risk classification applied to all MCP-imported tools by default. Teams that need fine-grained risk overrides on external tools must configure ApprovalPolicy manually — the docs describe the interface but provide precious little guidance on policy design for production environments, which is the condition under which teams switch to frameworks with more mature policy tooling.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Python 3.13
- API Available
- Yes
- Self-Hosted
- Yes
- Last Updated
- 2026-06-22T22:16:58.265Z
Best For
Who it's for
- Developers building self-directed agents
- Environments requiring risk-controlled execution
- Long-running autonomous planning loops
What it does well
- Autonomous multi-step task execution
- Codebase debugging and editing workflows
- Procedural skill acquisition and curation
- Controlled tool-using agents with audit trails
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Autonomy
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Autonomy free?
- Autonomy has a permanent free tier alongside paid upgrades (paid plans from $75/mo). You can keep using a baseline version indefinitely without paying.
- Is Autonomy open source?
- Yes. Autonomy is open source.
- Does Autonomy have an API?
- Yes. Autonomy exposes a developer API. See the official documentation at https://autonomy-landing-page.vercel.app for details.
- Can I self-host Autonomy?
- Yes. Autonomy supports self-hosting on your own infrastructure.
- What platforms does Autonomy support?
- Autonomy is available on: Python 3.13.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Autonomy is an open-source Python framework for building autonomous agents that plan, execute, and learn from their own runs without requiring a human to drive each step. The AgentLoop starts from a natural-language goal, pulls relevant ProcedureSkills from a library of 15 bundled skills, generates candidate action paths via a combination of LLM proposals and a RecipeEngine, scores them across five dimensions — evidence strength, purpose, risk, side effects, and penalty — then executes the top-ranked candidate through ActionGateway. Six explicit termination conditions (ACHIEVED, BLOCKED, NO_CANDIDATES, APPROVAL_DENIED, MAX_STEPS_REACHED, FAILED) ensure the agent cannot loop indefinitely.
The differentiating feature is the combination of ActionGateway and the post-run LearningLoop. Every tool call carries a RiskLevel and a verification plan before execution. After a successful run with at least two positive steps, LearningLoop automatically drafts a new ProcedureSkill at 0.85 confidence and generates a LearningProposal — which waits for review rather than self-applying. The RecipeEngine separately fingerprints successful actions via SHA-256 and promotes repeated patterns to reusable recipes, reducing LLM calls on familiar tasks over time.
The framework fits teams that need a verifiable, auditable agent for tasks like systematic debugging, TDD cycles, codebase documentation, or browser-based inspection — all covered by bundled skills. It fits less well when you need agents coordinating in parallel or a goal that branches into concurrent subgoals; the single AgentLoop design does not natively support multi-agent parallelism. Teams hitting that ceiling typically add an external orchestration layer, at which point they are managing two systems.
The toolset is extensible: file, terminal, search, and skills are enabled by default; browser (Playwright headless Chromium, 11 tools) and project tools (git, JSON, YAML) are opt-in; and external tools are importable via MCP through mcp_servers.yaml with MEDIUM risk classification applied automatically. Nine LLM providers are supported, including local Ollama and eight OpenAI-compatible endpoints, with an autonomy doctor command to verify endpoint connectivity.