Qodo (formerly Codium): Code Review

Founded 2022|Tel Aviv, Israel|51-200 people

What is Qodo (formerly Codium)?

Qodo (formerly CodiumAI) is an agentic code integrity platform that integrates AI across development workflows to strengthen code quality at every stage through automated code review, test generation, and documentation. Founded in 2022 by Itamar Friedman (formerly Alibaba Group's Director in their Israeli AI Lab) and Dedy Kredo (who previously led product and data science teams at Exploriem and VMware), the company has grown to employ 100 people across Israel, the US, and Europe by 2025. Qodo's platform consists of three main products: Qodo Gen for in-IDE code generation and test writing, Qodo Merge for pull request reviews, and Qodo Command for scripting and scheduling custom agents from the terminal or CI.

What sets Qodo apart is its proprietary Context Engine, which blends retrieval-augmented generation with custom code-embedding models, allowing agents to reason across huge monorepos without manual prompt engineering. The platform provides context-aware feedback that actually understands what the code is trying to do, not just surface-level issues. Users report that Qodo automates 80% of manual nitpicks in pull requests, resulting in significant time savings and catching issues early without slowing developers down.

Qodo has secured significant funding including $11 million in seed funding in 2023 and $40 million in Series A funding in 2024 led by Susa Ventures and Square Peg. Enterprise customers include Monday.com, Ford, and Intuit. The platform is SOC 2 Type II-audited and offers flexible deployment options including SaaS, on-premises, VPC, or fully air-gapped environments, with Teams/Enterprise data auto-purged within 48 hours.

Strengths and tradeoffs

What this tool does well, and the limitations to keep in mind.

Pros

Context-aware feedback that understands code intent, not just surface-level issues
Easy integration with IDE and Git workflows with minimal configuration required
Automates 80% of manual PR nitpicks, resulting in significant time savings
Full repository indexing provides enhanced context for better suggestions
Strong security with SOC 2 Type II compliance and flexible deployment options

Cons

Unit test cases often don't run on first attempt, requiring multiple iterations
Occasionally hallucinates and fails to understand context properly
Suggestions may miss the mark for very niche coding issues
Custom rule setup can take several days to configure
Premium pricing at $38/user/month makes it one of the more expensive options

Plans & pricing

What's included in each plan, and how the tiers compare.

Developer (Free)

Monthly

75 pull requests plus 250 LLM credits per month
Code review and test generation
Documentation and code autocomplete
Agentic coding tasks
Full repo indexing for enhanced context
Community support

Teams

$38

Per user/month

20 PRs per user monthly
2,500 IDE/CLI credits
All Developer features
21% savings with annual billing

Enterprise

Custom

Contact sales for a quote

Custom deployment options (on-prem, VPC, air-gapped)
SOC 2 Type II compliance
Data auto-purged within 48 hours
Context Engine with RAG
Custom support

View official pricing page

Using Qodo (formerly Codium) with Respan

Connect Qodo with Respan's observability platform to monitor AI-powered code reviews, track test generation quality, and analyze Context Engine performance across your codebase. Gain insights into review accuracy and optimize AI agent behavior.

Monitor PR review accuracy and track false positive rates across different code patterns
Analyze Context Engine performance and token usage for large monorepo operations
Track test generation success rates and identify patterns in failing tests
Debug AI hallucinations with detailed prompt and response logs
Compare performance across Qodo Gen, Merge, and Command products

Run Qodo (formerly Codium) in production with Respan

10KFree traces/mo

1,000+Models

5 minSetup

Respan lets you trace LLM and agent calls across any model or framework, A/B test prompts on production traffic, and route requests across 1,000+ models through one gateway.

Try Respan free