How much does Factory cost?

Pro $20/mo · Plus $100 · Max $200 (usage credits + 3 rolling rate limits; free Droid Core pool) · Teams/Enterprise custom · no free tier

What are the best alternatives to Factory?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to Factory among coding agents are GitHub Copilot, Kiro, OpenHands, Cursor. Each is graded on the same public evidence, and no vendor pays for placement.

Does Factory support MCP and tool calling?

Full under the Agentic Index verification standard. Factory publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: Agentic AI Index Expansion Evidence Report. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Factory have SOC 2, SSO and role based access control?

Full under the Agentic Index verification standard. Factory publishes public evidence of enterprise security and identity controls, covering a compliance posture such as SOC 2 or ISO 27001, single sign on (SSO or SAML), and role based access control (RBAC). Evidence basis: Agentic AI Index Expansion Evidence Report. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can Factory be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. Factory publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: Agentic AI Index Expansion Evidence Report. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Factory

Also known as: Factory Droid, Droids, Agent Readiness

Visit site

Coding agentindependentVerified 2026-06-28

Entry pricePro $20/mo · Plus $100/mo · Max $200/mo (usage-credit model; free Droid Core pool; prepaid Extra Usage $10 min) · Teams/Enterprise customFull pricing detail

Agent-native software development platform with Droid agents for automated code review, PR management, and engineering tasks.

Factory is an agent-native software development platform built around the idea that engineering work should be delegated to autonomous agents rather than typed line by line. Founded in 2023, the company calls its agents Droids, and they are designed to take on the full software lifecycle: planning, writing code, testing, reviewing, documenting, and shipping, along with larger jobs like refactors, migrations, and incident response. Unlike an in-editor assistant that suggests the next line, a Droid runs in the background and executes a whole task end to end while the developer works on something else.

Factory leans on specialized agents with explicit roles instead of one generalist. A coordinator decomposes a piece of work and dispatches it to droids focused on coding, review, documentation, testing, and knowledge, each passing structured output, such as diffs, review comments, and test results, to the next rather than loose conversation. A dedicated Knowledge layer indexes the repository, documentation, and ticket history so every droid shares the same understanding, and Factory's codebase representation gives agents deep, retrievable context about how a system fits together.

The natural unit of work is a ticket. Factory treats Linear and Jira as first-class entry points, pulling a ticket's description, acceptance criteria, comments, and linked context directly into the agent before it starts. Droids run inside sandboxed cloud environments that mirror the project's toolchain, and also locally through a desktop app and CLI for teams with or air-gapped requirements. Many droids can run in parallel, which is the point for large migrations and refactors that would otherwise be sequential.

Factory is model-agnostic and treats model choice as a routing problem: a router can select the most suitable model for each step and hand off between them within a single task, and the company emphasizes that strong agent design extracts more capability than model choice alone. The platform reaches developers through VS Code, JetBrains, the terminal, Slack, and pull-request automation, and is aimed at enterprise engineering teams, including regulated industries, that need autonomous, long-horizon work spanning many repositories and systems.

Vendor details

Canonical URL

https://factory.ai/

Company status

independent

Use cases & customers

Target customers

enterprisesdevelopers

Deployment options

SaaSself-hosted

In practice

You have a sprawling migration that would take one engineer weeks of repetitive edits. Factory runs multiple Droids in parallel, each taking a slice of the work end to end, instead of grinding through it sequentially.

Your team lives in Linear and Jira. Factory treats a ticket as the unit of work, pulling its description, acceptance criteria, and linked context into a Droid that implements the change and opens a pull request.

You want autonomous agents but your code can't leave your environment. Factory's Droids run in sandboxed cloud workspaces or locally through a desktop app and CLI, fitting teams with or air-gapped requirements.

Agentic Index coverage score

12.5 / 14 capabilities · 89%

Integrations & Tool CallingAgentic AI Index Expansion Evidence Report	Full
Workflow OrchestrationAgentic AI Index Expansion Evidence Report	Full
Knowledge Grounding & RAGAgentic AI Index Expansion Evidence Report	Partial
Human Oversight & GuardrailsAgentic AI Index Expansion Evidence Report	Full
Security, Identity & GovernanceAgentic AI Index Expansion Evidence Report	Full
Observability & AuditabilityAgentic AI Index Expansion Evidence Report	Full
Memory & State PersistenceAgentic AI Index Expansion Evidence Report	Partial
Deployment & Data ResidencyAgentic AI Index Expansion Evidence Report	Full
Prebuilt Agents, Templates & PacksAgentic AI Index Expansion Evidence Report	Full
Triggers & Channel CoverageAgentic AI Index Expansion Evidence Report	Partial
Model Flexibility & RoutingAgentic AI Index Expansion Evidence Report	Full
APIs, SDKs & MCP ExtensibilityAgentic AI Index Expansion Evidence Report	Full
Testing, Debugging & OptimizationAgentic AI Index Expansion Evidence Report	Full
Browser & Computer UseAgentic AI Index Expansion Evidence Report	Full

The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-07-14·Security / enterpriseVerified

Factory updated its Terms and Conditions for Individual Plans, detailing the licensing agreement for its AI coding platform and development tools. The revised terms explicitly state that customers grant Factory a non-exclusive license to access their connected codebases across platforms like GitHub, GitLab, and Bitbucket.

Bears on: Security / enterprise

View source

2026-07-01·Security / enterprisePartially Verified

Factory released Droid Shield 2.0 with two fine-tuned models for secret detection during autonomous commits, improving accuracy on real credentials versus false alarms while cutting latency and cost. Model weights were released for security research.

Bears on: Security / enterprise

View source

View all 2 changes for Factory →Tracked since Jul 2026 · Verified from public vendor sources

Pricing

Pro $20/mo · Plus $100/mo · Max $200/mo (usage-credit model; free Droid Core pool; prepaid Extra Usage $10 min) · Teams/Enterprise custom

hybrid

Included quota

Paid Individual (Pro $20 / Plus $100 / Max $200 per mo): Standard Usage (Factory Standard Credits) within rolling 5-hour / 7-day / 30-day Rate Limits, free Droid Core model pool, and a free BYOK allowance. Teams: tailored plans + basic admin controls (model selection, autonomy level, access controls, deny lists) - Contact Sales. Enterprise: custom onboarding, self-host/air-gapped - Contact Sales.

What is public

Factory (factory.ai - AI software-engineering agent platform: autonomous 'Droids' that handle coding/dev tasks across sessions and longer 'Missions'; supports frontier + open-weight models incl. GPT-5, Claude Opus/Sonnet, Gemini; self-host/air-gapped option for enterprise) publishes Individual plans: Pro $20/mo, Plus $100/mo, Max $200/mo (usage-credit model). Teams and Enterprise are custom (Contact Sales). No permanent free tier (Pro $20/mo is the entry).

Billing mechanics

Usage-credit subscription: Droid sessions consume 'Factory Standard Credits' based on model usage + compute for Droid Computers, governed by three rolling Rate Limits (5-hour, 7-day, 30-day, independent). 'Droid Core' (a pool of leading open-weight models) keeps you working at no extra cost on its own Rate Limits. 'Extra Usage' = prepaid pay-as-you-go credits ($10 minimum, rolls over) once included usage is exhausted. BYOK (bring-your-own-key) usage allowance included on Individual plans, then charged per plan.

Cost watchouts

Three independent Rate Limits (need headroom in all three to send a request); Standard Usage doesn't roll over; Missions require Extra Usage enabled (pause if a Rate Limit is hit); premium-model usage drains Standard Credits faster than Droid Core.

Variable cost rationale

Cost scales with model usage (Standard Credits) + compute (Droid Computers) + any prepaid Extra Usage; Droid Core offsets premium-model spend.

Additional watchouts

Usage-credit model + three rolling Rate Limits make cost forecasting model-dependent; Teams/Enterprise pricing not public; no free tier (Pro $20/mo to evaluate).

Overage / add-ons

When Standard Usage is exhausted, Droid Core models run on a separate free Rate-Limit pool; beyond that, prepaid Extra Usage credits ($10 min, roll over) are consumed. Standard Usage does not roll over month to month; purchased Extra Usage does.

Sales call required

Mixed (some tiers require a call)

Free / trial

n/p

Lowest paid plan

n/p (sales-led)

Commercial notes

AI software-engineering agent platform ('Droids'); ~$220M raised at ~$1.5B valuation (Series C led by Khosla, Apr 2026); competes with Cognition/Devin, Cursor, Claude Code, Augment Code, GitHub Copilot Workspace

Key ambiguities

Exact Standard-Credit allotments per Individual tier (Pro/Plus/Max) + Teams/Enterprise figures not fully public (Teams/Enterprise = Contact Sales); credit consumption varies by model choice (model multipliers) + task complexity. Older sources referenced a free plan, but recent sources indicate Pro $20/mo is the entry with no free tier.

Cancellation / refund

Self-serve paid Individual plans from $20/mo; prepaid Extra Usage ($10 min) rolls over; Teams/Enterprise via sales.

Support SLA / resale

Supports frontier + open-weight models (GPT-5, Claude Opus/Sonnet, Gemini); CLI/IDE/Desktop 'Droids'; self-host/air-gapped for enterprise; org admin controls on Teams+

Missing data

Individual pricing is published (Pro $20/mo, Plus $100, Max $200) with a usage-credit model (Factory Standard Credits metered by model usage + Droid Computer compute, governed by rolling 5-hour/7-day/30-day rate limits; free Droid Core open-weight pool; prepaid Extra Usage at $10 min that rolls over). Teams and Enterprise are custom (Contact Sales). Standard Usage doesn't roll over. No free tier (older 'free plan' references are stale).

Agentic Index verified 2026-06-25

Official pricing page

Related vendors

Alternatives to Factory

The closest documented capability profiles to Factory among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

GitHub Copilot12.5 / 14Fuller documented coverage on Knowledge Grounding & RAG and Triggers & Channel CoverageFactory vs GitHub Copilot →
Kiro10.5 / 14A lighter documented profile than Factory
OpenHands11.5 / 14Fuller documented coverage on Triggers & Channel Coverage
Cursor11.0 / 14Fuller documented coverage on Triggers & Channel CoverageFactory vs Cursor →
Google Antigravity10.0 / 14A lighter documented profile than Factory
JetBrains AI10.0 / 14A lighter documented profile than Factory

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Compare Factory with other vendors →Compare all coding agents →See where Factory ranks →

Data confidence: high

Head to head

Factory vs Cognition Factory vs Cosine Factory vs Augment Code Factory vs Cursor Factory vs Anthropic Claude Code Factory vs GitHub Copilot