# Alternatives to Devin > Source: https://theagentsindex.com/devin/alternatives (current datasheets, evidence-ranked) Candidates share the baseline category or are previously researched peers. Requirements, preserved strengths, explicit trade-offs and research coverage decide the order; paid tier does not. ## Shortlist ### 1. Augment Code Cosmos platform running fleets of coding agents across the SDLC, plus Auggie CLI and IDE extensions. **Research coverage:** 35/35 criteria **Where it improves on Devin:** - [Model choice: yes — You pick the model per expert, session or message; Prism routing is an opt-in alternative.](https://docs.augmentcode.com/models/available-models) - [Certifications: yes — SOC 2 Type II on both plans, ISO/IEC 42001 certified AI management system, GDPR and CCPA obligations in the terms.](https://www.augmentcode.com/security) **Trade-offs against Devin:** - [Open models: partial — Open-weight GLM and Kimi models are offered, but only Augment-hosted; the model list is closed and has no self-supplied weights.](https://docs.augmentcode.com/models/available-models) - [Free tier: partial — No free plan is published; pricing lists only Business at $100/month and Enterprise. Business is self-serve, though, and trials are referenced.](https://www.augmentcode.com/pricing) - [API access: partial — Auggie TypeScript/Python SDKs drive the agent from your own code; the Analytics API is Enterprise-only preview.](https://docs.augmentcode.com/cli/sdk) [View Augment Code](https://theagentsindex.com/augment-code) ### 2. Kilo Code Open source AI coding agent for VS Code, JetBrains, CLI and cloud, with 500+ models at provider rates. **Research coverage:** 35/35 criteria **Where it improves on Devin:** - [Model choice: yes — You pick the model; Auto Model routing is optional and never silently substitutes.](https://kilo.ai/auto-model) - [Open source: yes — VS Code extension, JetBrains plugin and CLI are MIT; the Gateway and Cloud backend are source available rather than MIT.](https://kilo.ai/open) - [Bring your own key: yes — Own provider keys at list price, shared org keys on Teams, or fully local inference.](https://kilo.ai/pricing) **Trade-offs against Devin:** - [Agent permissions: partial — Auto-approve exists, but the OS-level sandbox that bounds it is experimental and Linux/macOS only.](https://kilo.ai/enterprise) - [API access: partial — Cloud Agent sessions can be launched by HTTP webhook and usage data has documented OpenAPI endpoints; no public API for driving the agent itself is documented.](https://kilo.ai/cloud) - [Seat model: partial — Flat $15 per user per month with Owner and Member roles; no seat floor or ceiling is published.](https://kilo.ai/teams) [View Kilo Code](https://theagentsindex.com/kilo-code) ### 3. Codex CLI OpenAI's terminal coding agent for inspecting, editing and running repository code from the shell. **Research coverage:** 35/35 criteria **Where it improves on Devin:** - [Open source: yes — CLI, SDK and app server are in openai/codex; the IDE extension and Codex cloud are not open source.](https://learn.chatgpt.com/docs/open-source) - [Bring your own key: yes — Sign in with an OpenAI API key, or point the provider at Amazon Bedrock with AWS-native credentials.](https://learn.chatgpt.com/docs/auth) - [Certifications: yes — SOC 2 Type 2 report plus ISO 27001, 27017, 27018 and 27701 certification, with GDPR and CCPA listed on the trust portal.](https://trust.openai.com/) **Trade-offs against Devin:** - [Whole-codebase work: partial — Documented for repository-wide exploration and multi-step plans; the vendor states no repo-wide migration guarantee.](https://learn.chatgpt.com/docs/agent-configuration/subagents) - [Claude: no — Sign-in and model support are OpenAI models only; no Anthropic model appears in any documented model list.](https://learn.chatgpt.com/docs/auth) - [MCP server: partial — Codex is an MCP client for local and remote servers, but exposing Codex itself as an MCP server is deprecated in favour of the app server.](https://learn.chatgpt.com/docs/codex-sdk) [View Codex CLI](https://theagentsindex.com/codex-cli) ### 4. Factory Droid coding agents that run in the desktop app, CLI, IDEs, CI and Factory-managed cloud computers. **Research coverage:** 35/35 criteria **Where it improves on Devin:** - [Model choice: yes — You pick the model per session, per subagent and per exec run with -m/--model, or add custom endpoints.](https://docs.factory.ai/droid-exec/overview) - [Bring your own key: yes — BYOK covers your own OpenAI/Anthropic keys, OpenAI-compatible gateways, local models and AWS Bedrock; keys stay on your machine.](https://factory.com/pricing) - [Certifications: yes — SOC 2 Type II, ISO 27001 and ISO 42001, with reports and sub-processor lists in the Trust Center.](https://docs.factory.ai/enterprise/compliance-audit-and-monitoring) **Trade-offs against Devin:** - [Free tier: no — The published plan list starts at Pro $20/mo; no free tier or trial is offered, though Droid Core and a BYOK allowance are free within a paid plan.](https://docs.factory.ai/pricing/individuals) - [MCP server: partial — Droid is an MCP client over stdio/http/sse and can be driven by another program over JSON-RPC or ACP, but no Factory-hosted MCP server is documented.](https://docs.factory.ai/harness/mcp) - [Pooled budget: partial — Teams seats each keep their own Pro rate limits; Business and Enterprise usage is shared across the workspace.](https://docs.factory.ai/pricing/organizations) [View Factory](https://theagentsindex.com/factory-ai) ### 5. Cline Open-source coding agent for VS Code, JetBrains, the terminal and CI, running on whichever model you bring. **Research coverage:** 34/35 criteria **Where it improves on Devin:** - [Model choice: yes — You choose the model and the provider, and the vendor frames that as its differentiator; the same client talks to more than thirty providers plus local runtimes.](https://cline.bot/pricing) - [Self-hosted: yes — The client executes on your own machine by default, and Enterprise is documented for VPC, on-premises and air-gapped deployment with inference going straight to your providers.](https://cline.bot/enterprise) - [Open source: yes — The agent client and its SDK harness are published under the Apache 2.0 licence, and the paid layers are model access and organisation governance rather than the code.](https://cline.bot/) **Trade-offs against Devin:** - [In a browser: partial — The browser UI is Kanban, a board you start yourself on localhost and label a research preview; the vendor's hosted web app is the account and admin console, not a place to run tasks.](https://docs.cline.bot/usage/kanban) - [MCP server: partial — Cline is an MCP client - you attach local or remote servers to it, and a marketplace lists them - but the vendor documents no MCP server exposing Cline itself to another agent.](https://docs.cline.bot/mcp/mcp-overview) - [Seat model: partial — Seats are counted against an organisation licence - every owner, admin, member and even a pending invite holds one - but no seat price, floor or ceiling is published, and Enterprise claims unlimited seats.](https://docs.cline.bot/enterprise-solutions/team-management/managing-members) [View Cline](https://theagentsindex.com/cline) ### 6. OpenHands Open-source software engineering agent with GUI, CLI, SDK and an enterprise control plane. **Research coverage:** 34/35 criteria **Where it improves on Devin:** - [Model choice: yes — You choose the model on every tier; the vendor lists model agnosticism as a feature of the free local plan itself.](https://www.openhands.dev/pricing) - [Self-hosted: yes — Two self-host routes: the free open-source stack on your own machine, and Enterprise deployed into your own Kubernetes VPC.](https://www.openhands.dev/enterprise) - [Bring your own key: yes — Bring-your-own-key works on every plan, and Enterprise additionally runs on your own infrastructure with your existing provider agreements.](https://www.openhands.dev/pricing) **Trade-offs against Devin:** - [Whole-codebase work: partial — Repository-wide migrations are documented as prompts the agent handles, but the Large Codebase SDK that targets big repos is an Enterprise-only line on the pricing table.](https://www.openhands.dev/pricing) - [Multi-agent: partial — A parent agent can delegate to sub-agents, but the documented TaskToolSet runs them sequentially and blocks, so it is delegation rather than parallel coordination.](https://docs.openhands.dev/sdk/guides/task-tool-set.md) - [In your editor: partial — Zed, JetBrains and a community VS Code extension connect over ACP, but the vendor itself labels the IDE integration experimental.](https://docs.openhands.dev/openhands/usage/cli/ide/overview.md) [View OpenHands](https://theagentsindex.com/openhands) ## Method Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.