A developer's comparison of AI code-review tools finds that write-back capabilities—posting inline comments, resolving threads, applying suggestions, submitting reviews and merging—vary sharply by hos…
GitHub's ReviewBench, an open benchmark for AI code review agents built on 219 real pull requests across 19 programming languages, ranked GitHub Copilot first at 40.1% F1, but an independent benchmark…
An analysis of AI code review benchmarks found that vendor-published comparisons consistently rank their own tool first and report wildly different scores for the same rival, because each uses its own…
Slack introduced collaborative coding, a workflow that combines Slack Code channels with the CodeRabbit Agent for Slack so multiple human experts and AI agents can specify, plan, and build a coding ta…
CodeRabbit Security detected 86.7% of known vulnerabilities in an internal benchmark of 100 vulnerabilities across 94 repositories and 11 languages, ahead of Devin at 73.3%, Codex Security Plugin at 6…
CodeRabbit is positioning independent AI code review as the trust layer for agent-generated pull requests, cloning each repository into an isolated sandbox, building a code graph, and running more tha…
GitHits published a guide on October 5, 2026 detailing how to connect its MCP server to CodeRabbit so pull-request reviews can draw on open-source code and package data. The setup requires a GitHits p…
A developer built pr-proof, an open-source set of three Claude Code skills that validates AI code-review comments against the actual source before acting on them. Run against CodeRabbit's reviews of 5…
TypeSafe opened early access to Jev, its AI decision model for classification, scoring and routing, on September 15, and Vercel reported that nearly 13% of paid AI Gateway teams were using it within 2…
CodeRabbit's Agentic Change Management platform is now available through the OpenAI Marketplace, allowing OpenAI customers to apply their existing OpenAI spend commitment toward CodeRabbit purchases. …
Anthropic released Claude Sonnet 5.5 at the same price as Sonnet 5 ($2 per million input tokens, $10 per million output tokens), claiming 30% faster output and up to 30% lower cost per task. In CodeRa…
Cua AI tested seven models on 25 KiCad circuit-design tasks in its June evaluation, and the best-performing model completed only six of the 25 assignments despite being allowed up to 200 interaction s…
Two published AI code review benchmarks — LinearB's 16-bug, four-dimension evaluation and DeepSource's OpenSSF CVE Benchmark run against 200+ real production vulnerabilities — reach opposite conclusio…
CodeRabbit launched Change Stack, a pull request review tool that connects a PR's intent, behavior, and dependencies to the code itself, the company said in its announcement. Change Stack provides a P…
In an essay on AI harness engineering, developer Derek Wang argues that AI-generated code passes traditional CI gates because those gates only check syntax, while the real errors live in semantics. Ci…
Anthropic released Claude Opus 5.5, the first model in the Claude 5.5 family, and CodeRabbit's evaluation found both of its tested configurations caught slightly more open-source bugs than the product…
An AI agent-operated account built PR Rulebook, a local TypeScript CLI that mines accepted GitHub pull request review comments to compile a team's implicit code-review rules into ranked candidate rule…
AI research lab Martian has launched Code Review Bench, an open, MIT-licensed benchmark that scores AI code review tools on precision, recall, and F1 across 16,017 real open source pull requests where…
A comparison of 14 AI code review tools found that most cannot safely block a merge, with three offering no native merge-blocking mechanism at all, according to Codacy's 2026 analysis. The comparison …
A developer released a free, MIT-licensed GitHub Action that scans pull request diffs for malicious code using regex and semgrep rather than an LLM, targeting command execution, credential access, exf…