oss-fuzz-gen and circinus

These are competitors—both use LLMs to automatically generate fuzz test cases, with oss-fuzz-gen targeting OSS-Fuzz infrastructure while circinus appears to be a standalone fuzzer implementation, making them alternative approaches to the same problem.

oss-fuzz-gen
59
Established
circinus
36
Emerging
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 23/25
Maintenance 0/25
Adoption 6/25
Maturity 18/25
Community 12/25
Stars: 1,372
Forks: 208
Downloads: —
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 3
Forks: 1
Downloads: 21
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
Stale 6m

About oss-fuzz-gen

google/oss-fuzz-gen

LLM powered fuzzing via OSS-Fuzz.

Generates fuzz targets across C/C++, Java, and Python by prompting multiple LLMs (Vertex AI, Gemini, GPT-4) to synthesize harnesses, then evaluates them against OSS-Fuzz infrastructure using metrics like compilability, crash detection, and coverage gain versus human-written targets. The framework discovered 30+ real vulnerabilities including CVE-2024-9143 in OpenSSL, demonstrating LLM-generated targets can achieve up to 29% additional line coverage on production projects.

About circinus

PrVrSs/circinus

LLM-powered generation-based fuzzer.

Related comparisons

oss-fuzz-gen and ps-fuzz oss-fuzz-gen and PromeFuzz oss-fuzz-gen and fuzz4all oss-fuzz-gen and LLMFuzzer oss-fuzz-gen and LegoFuzz

Scores updated daily from GitHub, PyPI, and npm data. How scores work