CodeBurn

See where your AI coding spend actually goes

Developer ToolsArtificial IntelligenceGitHubOpen Source

▲ 101 votes11 commentsLaunched Aug 12, 2026

Visit Website

Daily #14Weekly #34

CodeBurn is a free, open-source tracker for AI coding costs. It reads the session files your tools already write - Claude Code, Cursor, Codex, Copilot, 40 in all, and shows every token and dollar by the task, model, project, and pull request that used it. The Optimize tab finds waste like cache bloat or retry tax, applies the fix, and tracks what it actually saved. Everything runs on your machine: no account, no uploads. MIT-licensed and genuinely free, used by 150k+ developers across the world.

AI Analysis

📝 Summary

CodeBurn is a free, open-source AI coding cost tracker that analyzes local session files from 40+ tools including Claude, Cursor, Copilot, and Codex. It delivers granular visibility into tokens and dollars spent by task, model, project, and pull request. The Optimize tab detects waste like cache bloat or retry tax, applies fixes automatically, and measures actual savings. Running entirely locally with no accounts or data uploads, it solves key pain points of opaque AI spending, hidden inefficiencies, and privacy risks in modern dev workflows. Its value proposition is empowering developers with full cost transparency and optimization while remaining MIT-licensed and genuinely free.

📈 Market Timing

With explosive growth in AI coding tools in 2025-2026, developer spend on models like Claude and GPT is surging, creating strong demand for precise cost tracking and waste reduction. Local AI tech is mature, privacy regulations are tightening, and teams seek better visibility amid rising costs. This is an Excellent Timing as cost management and optimization become priorities in AI-driven development.

✅ Feasibility

High. Technical implementation is proven (used by 150k+ developers) with local file parsing being straightforward. Operational costs are minimal as it runs on-user machines with no servers or cloud hosting required. Low compliance risks due to no data uploads. Open-source MIT model reduces development costs and aids scalability. Main challenge is ongoing compatibility with evolving AI tools.

🎯 Target Market

Primary users: Individual software developers, engineering teams, and open-source contributors using AI coding assistants. Industries: Software development, tech startups, enterprises with heavy GitHub usage. Geographic: Global with strong presence in US, Europe, and Asia. TAM for AI developer tools analytics exceeds $1B; SAM for cost trackers ~$200M; SOM for local/open-source segment ~$50M. Core pains: Untracked AI spend per project and inefficiencies. High willingness to pay for premium insights, though currently free.

⚔️ Competition

Low. Direct competitors: 1. Helicone (helicone.ai), 2. LangSmith (smith.langchain.com), 3. Arize Phoenix (arize.com/phoenix), 4. PromptLayer (promptlayer.com). Advantages: Fully local/privacy-first (no uploads vs cloud competitors), supports 40 tools, open-source/free with active optimization that applies fixes. Disadvantages: Lacks advanced team collaboration or hosted analytics dashboards offered by cloud platforms.

Upgrade Pro to unlock full AI analysis