agent-fuzzer 0.1.0

Adversarial scenario generation and testing for coding agents

AgentFuzzer

Adversarial scenario generation and testing for coding agents.

Quick Start

Quick Install

pip install agent-fuzzer

# Run fuzzing tests
agentfuzzer fuzz --model gpt-4 --count 20 --difficulty hard

# View report
agentfuzzer report -r fuzz_report.json

Scenario Categories

• broken_code: Code with bugs the agent must fix
• failing_tests: Tests that fail and need fixing
• missing_deps: Missing or conflicting dependencies
• network_errors: Network-related failures

License

MIT

Ecosystem

Part of the FableForge ecosystem — 21 open-source projects built from 210K real agent traces:

Project	Description
Anvil	Self-verified coding agent
VerifyLoop	Plan→Execute→Verify→Recover framework
ErrorRecovery	Self-healing middleware (3,725 error patterns)
FableForge-14B	The fine-tuned 14B model (4-stage training)
ShellWhisperer	1.5B edge agent (phone/RPi, 50ms)
ReasonCritic	Verification model (130 benchmark tasks)
TraceCompiler	Compile traces → LoRA skills
AgentRuntime	Persistent agent daemon (systemd for AI)
AgentSwarm	Multi-agent from real trace transitions
AgentTelemetry	Datadog for agents (token tracking, costs)
BenchAgent	HumanEval for tool-use (107 tasks)
AgentDev	VSCode extension with verification
TraceViz	Trace replay visualizer (Next.js)
AgentSkills	npm for agent behaviors
AgentCurriculum	5-stage progressive training
AgentFuzzer	Adversarial testing for agents
AgentConstitution	Safety guardrails from traces
CostOptimizer	Token cost reduction (50-80%)
AgentProfiler	Behavioral fingerprinting
TrajectoryDistiller	Trace→training data pipeline
Fable5-Dataset	HuggingFace dataset release