AI bug finder

Editorial picks for "ai bug detector".

13 tools

All Coding →

Devin

Agents · Multi-model (Claude / GPT configurable)

7.8

Cognition Labs' "autonomous software engineer" agent.

Paid· From $500/mo Coreautonomous codingticket resolution

mini-SWE-agent

Agents · Multi-model (via litellm, OpenRouter, Portkey)

7.2

A 100-line open-source coding agent that scores 74%+ on SWE-bench Verified.

Free· Free and open source (Apache 2.0); you pay only for the underlying LLM tokens.swe-bench-evaluationautonomous-coding

Qodo (formerly CodiumAI)

Coding · Multi-model (Claude, GPT, Gemini, NVIDIA)

7.2

AI code review and test generation platform that plugs into IDEs, pull requests, and CLI with deep multi-repo context.

Freemium· Pro Team: $30 · Custom plan: ?code-reviewtest-generation

Codeflash

Coding · Multi-model

7.0

Autonomous AI performance engineer that finds and PRs code optimizations with benchmarks attached.

Freemium· Free: $0 · Pro: $20 · Enterprise: Custom pricingcode-optimizationgpu-cuda-kernels

CodeRabbit

Coding · Multi-model

7.0

AI pull-request reviewer that lives inside GitHub, GitLab, and your IDE.

Freemium· Pro: $24/mo/user · Pro Plus: $48/mo/user · Enterprise: Contact us · Free: $0/mo/usercode-reviewpr-automation

SWE-agent

Agents · Multi-model (GPT-4o, Claude Sonnet, DeepSeek, local via LiteLLM)

7.0

Open-source autonomous agent framework that lets LLMs fix GitHub issues and find security vulnerabilities by using a custom agent-computer interface.

Free· Free and open-source; you pay your own LLM API costsgithub-issue-fixingautonomous-coding

Callstack.ai PR Reviewer

Coding

6.9

AI pull request reviewer that flags bugs, security issues, and style drift against your team's own guidelines.

Freemium· Basic: $10 · Pro: $20 · Enterprise: Contact salespr-reviewbug-detection

Cobalt

Coding · Agent-agnostic wrapper: OpenAI Codex (via user's ChatGPT account), Claude Code, Cursor, OpenCode, Pi

An AI developer with its own cloud computer that writes code in your GitHub repo, runs the tests, and hands you a pull request.

Freemium· Public pricing not listed on the marketing site at time of review; a free 'Try Cobalt' onboarding is offered and users bring their own ChatGPT account (Plus/Pro) to power the Codex coding agent, so model-provider costs sit outside Cobalt.Async feature implementation via pull requestReproduce-and-fix bug tickets end-to-end

Factory AI (Droids)

Coding · Model-agnostic: GPT-5, Claude Opus/Sonnet, Gemini, plus open-weight models

Agent-native platform that runs the whole software development lifecycle with autonomous Droids.

Freemium· Pro: $20 · Plus: $100 · Max: $200 · Business: ? · Enterprise: ?Autonomous ticket-to-PR feature workLarge-scale codebase refactors

getdebug

Coding

AI-powered codebase analyzer and auto-fixer that ships validated PRs

Freemium· Free: $0 · Pro: $39/ dev / mo · Pro Plus: $79/ dev / mo · Custom: Let's talk · Pay as you go: Base + usageAutomated bug-fix pull requestsSecurity vulnerability remediation

Greptile

Coding

AI code review that understands the whole codebase, not just the diff

Paid· Starter: Free · Pro: $30/seat/month · Enterprise: Custom pricingAutomated pull request reviewCross-file bug detection

Kritt

Agents · Codex and Claude Code (as agent harnesses)

AI-assisted code security research with parallel agents and verified findings

Freemium· Single Scan: $5,000 per scan · Enterprise: Contact usPre-launch security audit of a new serviceContinuous vulnerability scanning in CI/CD

Sentry MCP

MCP Servers · Bring-your-own LLM (OpenAI, Anthropic, Azure OpenAI, or OpenRouter) for natural-language search skills; agent-side model is whatever your MCP client runs.

Official Sentry MCP server: give Claude Code, Cursor, and other AI agents real access to your errors, traces, and triage.

Freemium· Free: $0 USD · Team: $4 USD per user/month · Enterprise: $21 USD per user/monthDebug production error from IDE agentRoot-cause a latency regression via trace lookup