wolfpld/tracy

Frame profiler

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 34 minutes ago
Added to GitGenius on November 22nd, 2025
Created on March 17th, 2020
Open Issues & Pull Requests: 166 (+0)
Number of forks: 1,223
Total Stargazers: 16,660 (+0)
Total Subscribers: 134 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 13.2 hours
Mean response time: 149.4 days
90th percentile: 683.8 days
Tracked items: 406

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 97% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Only 10% of issues opened in the past year have been closed. Three people close 76% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 129
New in 7 days: 0
Closed in 7 days: 30
Avg open age: 598 days
Stale 30+ days: 119
Stale 90+ days: 115

Recent activity

Opened in 7 days: 0
Closed in 7 days: 23
Comments in 7 days: 7
Events in 7 days: 12

Top labels

  • enhancement (72)
  • bug (36)
  • awaiting response (10)
  • documentation (10)
  • help wanted (9)
  • windows (8)
  • good first issue (6)
  • question (6)

Detailed Description

Tracy is a real-time profiler designed for games and other applications, offering nanosecond resolution telemetry and hybrid frame and sampling profiling capabilities. Written in C++, it provides remote profiling functionality that allows developers to analyze performance data from running applications across network connections. The profiler supports multiple profiling domains including CPU, GPU, memory allocations, locks, and context switches, making it a comprehensive tool for performance analysis in complex applications.

The profiler offers direct integration support for C, C++, Lua, Python, and Fortran, with third-party bindings available for numerous other languages including Rust, Zig, C#, OCaml, and Odin. GPU profiling extends across all major graphics and compute APIs including OpenGL, Vulkan, Direct3D 11 and 12, Metal, OpenCL, CUDA, and WebGPU. Beyond traditional profiling metrics, Tracy includes distinctive features such as the ability to automatically attribute screenshots to captured frames, providing visual context for performance analysis.

The repository maintains active development with substantial community engagement.

This cross-pollination suggests the profiler has gained adoption among developers working with multiple programming languages and platforms. The project provides comprehensive documentation available in PDF format through its releases, along with compiled Windows x64 binaries for immediate use.

The profiler's evolution is well-documented through a series of feature introduction videos spanning versions 0.2 through 0.8, with a notable CppCon 2023 presentation by Marcos Slomp providing an introduction to Tracy's capabilities in the C++ context. An interactive demo is available on the project's website at tracy.nereid.pl, allowing potential users to explore the profiler's interface and capabilities before integration. The combination of comprehensive profiling features, multi-language support, remote telemetry capabilities, and active maintenance positions Tracy as a significant tool in the performance analysis landscape for game development and other performance-critical applications.