Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
Python agentsai-hackingai-penetration-testingai-pentestingai-securityartificial-intelligencebug-bountycode-qualityctf-toolscybersecuritycybersecurity-toolsethical-hackinghackingllm-securityoffensive-securitypenetration-testingpentesting-toolsred-teamingsecuritysecurity-automation
Commits on main
fix(tui): drop the shift+enter newline hint from the setup footer
6f70b6f Ahmed Allam committed 3 months ago
feat(tui): replace Textual with a Go/Bubble Tea interface (#941)
5bb9fe8 oyasumi committed 3 months ago
fix: calibrate vulnerability severity to demonstrated impact
a51ca18 bearsyankees committed 3 months ago
feat(runtime): mount local targets instead of copying them in (#958)
dbc427d devin-ai-integration[bot] committed 3 months ago
fix(tools): tell a waiting parent when stop_agent stops its child
b6cf156 Ahmed Allam committed 3 months ago
fix(core): wake the parent when a child ends without a completion report
0027122 Ahmed Allam committed 3 months ago
perf(cli): ~10x faster startup via lazy imports (#920)
797b374 devin-ai-integration[bot] committed 3 months ago
fix(tools): accept both the string and structured form of every tool argument (#957)
c240068 devin-ai-integration[bot] committed 3 months ago
feat(config): accept STRIX_REASONING_EFFORT=max for providers that support it (#956)
2e70402 devin-ai-integration[bot] committed 3 months ago
docs(llm-providers): explain the structured tool_calls requirement for local endpoints (#520) (#901)
22d668d devin-ai-integration[bot] committed 3 months ago
docs(prompts): text-only turns no longer end an autonomous run
f77805e Ahmed Allam committed 3 months ago
refactor(tools): split wait_for_message into respond_to_user + wait_for_agents
1c1fa49 Ahmed Allam committed 3 months ago
docs(core): correct the rationale for notifying a stalled child's parent
742f382 Ahmed Allam committed 3 months ago
fix(core): tell the parent when an interactive subagent parks
8f1bb64 Ahmed Allam committed 3 months ago
fix(core): persist the tool-call recovery counter across resumes
6eec34d Ahmed Allam committed 3 months ago
fix(core): stop interactive runs stalling on a missing tool call
f6f9469 Ahmed Allam committed 3 months ago
docs(prompt): teach agents to recognize Caido proxy error pages instead of chasing them (#955)
dc7cc50 devin-ai-integration[bot] committed 3 months ago
fix: pre-v1-style lifecycle resilience — mailbox delivery, uniform revival, unexitable runner, waiting timeout, broader retries, crash-safe identity (#923)
5602bc2 devin-ai-integration[bot] committed 3 months ago
test(llm): cover the full run loop against a non-streaming gateway; drop README note
885b2ca Ahmed Allam committed 3 months ago
feat(llm): opt-in LLM_DISABLE_STREAMING for non-streaming OpenAI-compatible endpoints
9802168 Ahmed Allam committed 3 months ago
fix(llm): pass LLM_EXTRA_HEADERS through ModelSettings so they reach the agent loop (#937)
d4e58b2 devin-ai-integration[bot] committed 3 months ago
fix(llm): apply LLM_EXTRA_HEADERS on native OpenAI route even without a custom base
e9ebdc5 Ahmed Allam committed 3 months ago
feat(llm): custom request headers for OpenAI-compatible endpoints via LLM_EXTRA_HEADERS
ebb3a62 Ahmed Allam committed 3 months ago
fix(runtime): label docker sandbox containers with the run id for teardown (#933)
1a2fa89 devin-ai-integration[bot] committed 3 months ago
fix(cost): capture OpenRouter streamed usage.cost (fixes $0 kimi-k3 c… (#929)
9de747d alex s committed 3 months ago