CataleoSoftware
Get Your Software Listed Get Listed

AI

AI Code

AI coding assistants and agents that help developers write, refactor and ship code. Every tool below is measured against the same criteria, in the same order. Note that this field moves fast, so treat every value as a snapshot and check it against the vendor before you rely on it.

Filters

AI
Deployment
Company Size
Industry

31tools

  • OpenHands

    Price Free, open source (MIT)

    Not rated yet

    Open-source platform for software engineering agents, self-hosted or run as a managed cloud service.

    Strengths

    • Open source under MIT, so it can be self-hosted, audited and modified
    • Model-agnostic through LiteLLM, including local open-weight models
    • One agent available as a web interface, a CLI, an SDK and a hosted cloud service

    Limitations

    • No inline code completion; it is an agent platform, not an editor assistant
    • Self-hosting means supplying and paying for your own model access
    • The free hosted tier is capped at 10 conversations per day
    Visit site

  • Roomote

    MCP-ready

    Price Free for up to 10 self-hosted users; cloud from $49 / month

    Not rated yet

    A source-available cloud coding agent that runs in your own deployment and hands back reviewed pull requests.

    Strengths

    • Self-hostable and single-tenant, with your own inference keys and sandbox provider
    • Work starts and lands in Slack, Teams, Discord, Telegram, Linear or a pull request rather than in an editor
    • Reviews its own changes with a second model and returns a live preview URL before a human looks

    Limitations

    • No inline completions and no editor integration; it is not a local assistant
    • Self-hosting means running the deployment, the sandboxes and the inference bill yourself
    Visit site

  • Devin

    Price Free tier; Pro $20 / month

    Not rated yet

    An autonomous AI software engineer that takes tickets to pull requests in the cloud.

    Strengths

    • Works asynchronously in the cloud, so it can run tasks without occupying your editor
    • Takes whole tickets end to end, from Linear or Jira through to a pull request
    • Reachable from Slack, Teams, a CLI, a web app and an API, not only an IDE

    Limitations

    • Consumption-based ACU billing makes heavy use harder to predict than a flat seat price
    • Aimed at delegable, self-contained tasks rather than interactive pair programming
    Visit site

  • Amazon Q Developer

    Price Perpetual free tier; Pro $19 / user / month

    Not rated yet

    AWS's AI coding assistant, deeply integrated with the AWS ecosystem (formerly CodeWhisperer).

    Strengths

    • Deep AWS integration
    • Perpetual free tier
    • Strong for AWS-native work

    Limitations

    • General-purpose coding trails the leaders
    • Most value inside AWS
    Visit site

  • Factory

    Price From $20 / month

    Not rated yet

    An enterprise platform for agentic software development, built around agents it calls Droids.

    Strengths

    • Autonomous agents across desktop, CLI and an SDK
    • Enterprise controls: SSO, zero data retention, on-premise option
    • Cloud and local background agents

    Limitations

    • No free tier
    • Aimed at teams rather than individual developers
    Visit site

  • GitHub Copilot

    Price Free tier; Pro $10 / month

    Not rated yet

    The most widely adopted AI coding assistant, integrated across major IDEs and GitHub.

    Strengths

    • Most widely adopted and easy to get approved
    • Widest IDE support
    • Free tier
    • IP indemnity

    Limitations

    • Agent and multi-file orchestration trail Cursor and Claude Code
    • New usage-based credits can raise heavy-use cost
    Visit site

  • Jules

    Price Free tier

    Not rated yet

    Google's asynchronous coding agent that works in the cloud and opens pull requests on GitHub.

    Strengths

    • Runs asynchronously in the cloud, no local setup
    • Integrates directly with GitHub and opens pull requests
    • Free tier for light use

    Limitations

    • Tied to Gemini models, no other model choice
    • Higher limits require a Google AI subscription
    • Asynchronous only, not an interactive editor
    Visit site

  • Greptile

    MCP-ready

    Price Free tier; Pro $30 / seat / month

    Not rated yet

    AI code review that indexes the whole codebase and comments on every pull request.

    Strengths

    • Reviews with whole-codebase context from a graph index, not only the diff
    • Learns a team's standards from the comments its own engineers leave on pull requests
    • Self-hosting in your own AWS account with your own model providers on Enterprise

    Limitations

    • Billed per seat receiving reviews, so cost follows team size
    • Full quality covers a fixed list of languages; others work at reduced quality
    • No model choice unless you self-host on Enterprise
    Visit site

  • Augment Code

    Price Standard $20 / month

    Not rated yet

    An agentic coding platform built around a deep codebase context engine, in the IDE and the terminal.

    Strengths

    • Strong codebase context engine for large repositories
    • Model choice across Claude and Gemini with a cost and quality router
    • Works in VS Code, JetBrains and a terminal CLI

    Limitations

    • Sold to teams rather than individuals, with a flat plan price on top of usage
    • Usage beyond the included amount is billed on top
    • Inline completions are Enterprise-only since March 2026
    Visit site

  • CodeRabbit

    Price Free for open-source repos; Pro $24 / user / month

    Not rated yet

    AI code review that comments on every pull request, proposes one-click fixes and ranks the queue by risk.

    Strengths

    • Reviews every pull request automatically and proposes one-click fixes
    • Covers GitHub, GitLab, Bitbucket and Azure DevOps, including self-managed servers
    • Free reviews for public and open-source repositories
    • Customer code is not used for training, and Enterprise can self-host

    Limitations

    • Reviews code rather than writing it, so it sits alongside a coding assistant rather than replacing one
    • Hourly review caps per developer: 5 pull requests on Pro, 10 on Pro Plus
    • Self-hosting is Enterprise only and starts at 500 seats
    • Security monitoring is a separate $40 per user per month tier
    Visit site

  • OpenAI Codex

    Price Included with ChatGPT Plus $20 / month

    Not rated yet

    OpenAI's coding agent, in the terminal, the IDE, the cloud and on pull requests.

    Strengths

    • One agent and one allowance across the terminal, IDE, cloud and pull requests
    • Bundled into existing ChatGPT plans, easy to reach if you already pay for ChatGPT
    • Cloud sandbox runs longer tasks asynchronously while you keep working

    Limitations

    • Tied to OpenAI's own models, with no third-party model choice
    • Token-based credits mean heavy use can need extra purchases; the free and Go tiers are limited
    Visit site

  • Goose

    Price Free, open source

    Not rated yet

    Open-source AI agent that runs on your own machine and extends through MCP.

    Strengths

    • Free and open source under Apache 2.0, with no paid tier
    • Runs locally and can be pointed at local models, so code need not leave the machine
    • Vendor-neutral governance under the Linux Foundation
    • Recipes make a workflow portable across a team and runnable in CI/CD

    Limitations

    • No inline code completion and no editor of its own
    • You supply and pay for model access yourself
    • Setup and upkeep are on the user, with no hosted service to fall back on
    Visit site

  • Google Antigravity

    Price Free tier

    Not rated yet

    Google's agent-first development platform, with an IDE, a CLI and a Python SDK.

    Strengths

    • Free for individual developers, with unlimited tab completions and command requests
    • Third-party models alongside Gemini, including Claude Sonnet 4.6 and Opus 4.6
    • Agent command centre, IDE, CLI and Python SDK in one product
    • Agents can be scoped to a project or run in an isolated Git worktree

    Limitations

    • The pricing page names the Google AI Pro and Ultra tiers without stating what they cost
    • Enterprise plans drop the Claude and GPT models
    • The free plan is bounded by weekly rate limits
    Visit site

  • Aider

    Price Free, open source

    Not rated yet

    Open-source AI pair programming in your terminal that edits your code and commits to git.

    Strengths

    • Free and open source, works with almost any LLM including local models
    • Edits across multiple files and auto-commits to git with sensible messages
    • Editor-agnostic, runs in the terminal alongside any IDE

    Limitations

    • You supply and pay for your own LLM API keys
    • Terminal-first, with no graphical IDE of its own
    • No inline autocomplete
    Visit site

  • Refact.ai

    Price Free tier; Pro $10 / month

    Not rated yet

    An open-source AI coding agent with chat and autocomplete, and a self-hosted option.

    Strengths

    • Open source with a self-hosted, on-premise option
    • Agent, chat and completion in one plugin
    • Broad model choice through bring-your-own-key

    Limitations

    • Free plan caps daily agent runs
    • Some IDE plugins are still in beta
    Visit site

  • Gemini Code Assist

    Price From $19 / user / month

    Not rated yet

    Google's AI coding assistant for the IDE, with agentic chat and enterprise code customization.

    Strengths

    • Backed by Google, with broad IDE coverage
    • Agentic chat that can call system tools and MCP servers
    • Enterprise edition customizes suggestions on your private repositories

    Limitations

    • No free individual tier since June 2026
    • Most value inside the Google Cloud and Gemini ecosystem
    Visit site

  • Tabby

    Price Free and open source, Apache 2.0

    Not rated yet

    An open-source, self-hosted AI coding assistant you run on your own infrastructure.

    Strengths

    • Fully open source under Apache 2.0
    • Runs entirely self-hosted, so code stays on your infrastructure
    • Works across more than a dozen editors on consumer-grade GPUs

    Limitations

    • You host, run and maintain the models yourself
    • Needs your own GPU hardware
    Visit site

  • Qoder

    Price Free tier; Pro $20 / month

    Not rated yet

    An agentic coding platform with an IDE, a JetBrains plugin, a CLI and managed cloud agents, metered in credits.

    Strengths

    • In-editor assistance and long-running agent delegation come from one product family and one account
    • Model tiers and named models carry published credit rates, with a free Lite tier and personal API keys accepted
    • ISO/IEC 27001:2022 certified and SOC 2 Type II audited, with privacy mode and audit logs on the organisation plans

    Limitations

    • Every paid plan is metered in credits, and running out drops the account to basic models with a daily limit
    • Qoder and Qoder IDE are separate products with separate conversation history and memory, which has to be imported between them
    Visit site

  • Zed

    Price Free; Pro $10 / month

    Not rated yet

    Open-source, high-performance code editor with agentic AI editing and edit prediction.

    Strengths

    • Fast, native, open-source editor
    • Agentic AI editing with a free plan and a bring-your-own-key option
    • Model choice across Anthropic, OpenAI, Google and more

    Limitations

    • Younger ecosystem than established IDEs
    • Hosted AI beyond the included credit is billed by token
    Visit site

  • Mistral Vibe for Code

    Price Free tier; Pro $14.99 / month

    Not rated yet

    Mistral's coding agent for the terminal, the IDE and the web, deployable on your own infrastructure.

    Strengths

    • Self-hosted, on-premises and VPC deployment alongside the cloud service
    • Inline completions and a multi-file agent in one product, across CLI, IDE and web
    • Pro costs $14.99 per month and includes $15 per month in API credits
    • Async agents continue a task after the session ends

    Limitations

    • Mistral models only, with no third-party model choice
    • Team billing carries a minimum of $50 per month regardless of seat count
    • The free plan limits messages and web searches
    Visit site

  • Cursor

    Price Free tier; Pro $20 / month

    Not rated yet

    An AI-native code editor (a VS Code fork) built around agentic multi-file editing.

    Strengths

    • Best AI-integrated editing experience
    • Maturest AI-native IDE ecosystem
    • Multi-model choice

    Limitations

    • Requires switching editors, which means IDE lock-in
    • Power tiers get expensive
    Visit site

  • JetBrains AI Assistant

    Price Free tier; AI Pro $20 / month

    Not rated yet

    AI assistant and the Junie coding agent built into JetBrains IDEs, under one subscription.

    Strengths

    • Deeply integrated into JetBrains IDEs and their refactoring and inspection tools
    • One subscription covers AI Assistant and the Junie agent, and external agents can be driven from the same chat
    • Local models via Ollama or LM Studio work for chat, generation, commit messages and documentation
    • The credit quota is denominated in dollars, so usage is legible before it runs out

    Limitations

    • Only useful inside JetBrains IDEs, and AI Free is unavailable in Android Studio and the Community editions
    • Cloud features are metered by a monthly AI credit allowance, with top-ups sold separately
    • The plugin is not bundled and is disabled by default, so it has to be installed and enabled
    Visit site

  • Tabnine

    Price Pro $12 / month

    Not rated yet

    Privacy-first AI coding assistant with self-hosted and air-gapped deployment.

    Strengths

    • Only major tool with air-gapped self-hosting and zero data retention
    • Custom models on your own repositories
    • Broad IDE support

    Limitations

    • AI quality trails the leaders for agentic work
    • Annual commitment, no monthly plan
    Visit site

  • Cline

    Price Extension free, Apache 2.0

    Not rated yet

    An open-source, bring-your-own-key AI coding agent for VS Code.

    Strengths

    • Fully open-source and free extension
    • Use any model or provider
    • Can run fully local for privacy and zero API cost

    Limitations

    • You manage model keys and API costs
    • Less polished than commercial IDEs
    • More setup
    Visit site

  • Kilo Code

    Price Free and open source; Teams $15 / user / month

    Not rated yet

    An MIT-licensed coding agent for VS Code, JetBrains, the terminal and the cloud, with model calls billed at provider rates.

    Strengths

    • MIT licensed, with the prompt, context window and decisions open to inspection
    • Model calls billed at exact provider rates with no markup, or run on your own keys and local models
    • One account across VS Code, JetBrains, the CLI, cloud agents, Slack and mobile

    Limitations

    • Usage is metered per model call rather than per seat, so budgeting takes attention
    • Kilo Deploy has reached end of life and is closed to new users
    Visit site

  • Kiro

    Price Free tier; Pro $20 / user / month

    Not rated yet

    An agentic, spec-driven IDE from AWS that turns prompts into specs, code and tests.

    Strengths

    • Spec-driven flow documents requirements before coding
    • Based on Code OSS, imports VS Code settings and Open VSX plugins
    • Model choice including Claude, open-weight models and Auto routing

    Limitations

    • Credit-based usage on every tier
    • Newer product with a smaller ecosystem than established IDEs
    Visit site

  • Qodo

    Price Pro Team $30 / month

    Not rated yet

    AI code review and context-aware suggestions across the IDE, pull requests and Git workflows (formerly CodiumAI).

    Strengths

    • Automated, context-aware code review in the IDE and pull requests
    • Bring-your-own-model and self-hosted options on Enterprise
    • Broad Git platform coverage across GitHub, GitLab, Bitbucket and Azure DevOps

    Limitations

    • Credit-based pricing can be harder to predict
    • Focused on review and quality more than full IDE autocomplete
    Visit site

  • Amp

    Price Megawatt $20 / month

    Not rated yet

    Sourcegraph's agentic coding tool, a frontier agent across the terminal, editors and Slack.

    Strengths

    • Agent-first workflow that spans the terminal, multiple editors, the web and Slack
    • Routes between frontier and fast models instead of locking to one
    • Thread sharing makes agent work collaborative across a team

    Limitations

    • Usage-based pricing can be harder to predict than a flat seat price
    • Built around an autonomous agent rather than inline autocomplete
    Visit site

  • OpenCode

    Price Free, MIT licence

    Not rated yet

    An MIT-licensed AI coding agent for the terminal, the desktop and the IDE.

    Strengths

    • MIT-licensed and free, with no restriction on commercial use
    • More than 75 model providers plus fully local models, so no vendor lock-in
    • One agent across terminal, desktop app and IDE
    • Local server and TypeScript SDK for embedding the agent in other tools

    Limitations

    • You manage provider keys and pay model costs directly, so spend is harder to predict than a seat price
    • Topping up OpenCode Zen credit adds a card processing fee of 4.4% plus $0.30 per transaction
    • Zen model prices span a wide range, from $0.05 to $180 per million tokens depending on the model
    Visit site

  • Warp

    Price Free tier; Build $20 / month

    Not rated yet

    An agentic terminal for AI-assisted development, with coding agents alongside your shell.

    Strengths

    • Coding agents and shell in one terminal
    • Multiple model providers
    • Cross-platform: macOS, Linux and Windows

    Limitations

    • Terminal-based workflow, not an in-editor experience
    • Agent usage is metered by credits
    Visit site

  • Claude Code

    Price Included in Claude Pro, $20 / month

    Not rated yet

    Anthropic's terminal-native coding agent for complex, multi-file work and architectural reasoning.

    Strengths

    • Deepest reasoning for complex multi-file and architectural tasks
    • Project-level planning
    • Editor-agnostic

    Limitations

    • Terminal-first, not a full IDE interface
    • Usage limits on Pro, and cost climbs on Max or heavy API use
    Visit site

Direct Comparisons