What’s New

strix

AIAndroid

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

Latest v1.4.1 · · Androidby usestrixWebsiteusestrix/strix

Release activity

Release activity — 10 releases across 7 days since May 27, 2026. Each cell is one day; darker means more releases that day. Nothing is recorded before May 27, 2026.
AugSepOctNovDecJanFebMarAprMayJunJulAug
SundayNo releases on May 31, 2026No releases on Jun 7, 2026No releases on Jun 14, 2026No releases on Jun 21, 2026No releases on Jun 28, 2026No releases on Jul 5, 2026No releases on Jul 12, 2026No releases on Jul 19, 2026No releases on Jul 26, 2026No releases on Aug 2, 2026
MondayNo releases on Jun 1, 2026No releases on Jun 8, 2026No releases on Jun 15, 2026No releases on Jun 22, 2026No releases on Jun 29, 2026No releases on Jul 6, 2026No releases on Jul 13, 2026No releases on Jul 20, 20262 releases on Jul 27, 2026No releases on Aug 3, 2026
TuesdayNo releases on Jun 2, 20262 releases on Jun 9, 2026No releases on Jun 16, 2026No releases on Jun 23, 2026No releases on Jun 30, 2026No releases on Jul 7, 20261 release on Jul 14, 20261 release on Jul 21, 2026No releases on Jul 28, 2026
Wednesday1 release on May 27, 2026No releases on Jun 3, 2026No releases on Jun 10, 2026No releases on Jun 17, 2026No releases on Jun 24, 2026No releases on Jul 1, 2026No releases on Jul 8, 2026No releases on Jul 15, 20262 releases on Jul 22, 2026No releases on Jul 29, 2026
Thursday1 release on May 28, 2026No releases on Jun 4, 2026No releases on Jun 11, 2026No releases on Jun 18, 2026No releases on Jun 25, 2026No releases on Jul 2, 2026No releases on Jul 9, 2026No releases on Jul 16, 2026No releases on Jul 23, 2026No releases on Jul 30, 2026
FridayNo releases on May 29, 2026No releases on Jun 5, 2026No releases on Jun 12, 2026No releases on Jun 19, 2026No releases on Jun 26, 2026No releases on Jul 3, 2026No releases on Jul 10, 2026No releases on Jul 17, 2026No releases on Jul 24, 2026No releases on Jul 31, 2026
SaturdayNo releases on May 30, 2026No releases on Jun 6, 2026No releases on Jun 13, 2026No releases on Jun 20, 2026No releases on Jun 27, 2026No releases on Jul 4, 2026No releases on Jul 11, 2026No releases on Jul 18, 2026No releases on Jul 25, 2026No releases on Aug 1, 2026

10 releases since May 27, 2026, busiest day 2

Changelog

v1.4.1

Fixed 1
  • Replace raw urllib with requests for external HTTPS calls to resolve frozen-build cert failures
What's Changed

Full Changelog: https://github.com/usestrix/strix/compare/v1.4.0...v1.4.1

View originalPermalink

v1.4.0

Added 7
  • Add strix --update command for self-updating the CLI
  • Add sign in with ChatGPT subscription for inference
  • Add dedicated deduplication model
  • Add read-only list_reports and get_report tools
  • Add Linux ARM64 standalone release support
  • Enable Bedrock/Anthropic prompt caching for Claude models
  • Add graduated wrap-up warnings, budget reserve, and interactive budget pause/continue
Changed 7
  • Update CLI notifications
  • Quit after scan instead of hosting local viewer
  • Rename root agent to Strix
  • Move strix/viewer under strix/interface
  • Bound per-tool output before it enters agent history
  • Implement model-aware conversation compaction for long scans
  • Spill oversized tool output into the sandbox workspace
Fixed 6
  • Cap cryptography <49 to keep Intel macOS universal2 wheel
  • Strip markdown code fence from poc_script_code before rendering in reports
  • Resolve staged local-dir path to avoid symlink rejection on macOS
  • Retry transient mid-stream provider errors instead of crashing the scan
  • Don't dump raw warm-up traceback over the LLM error panel
  • Wake parent when a child hits a terminal state (MaxTurnsExceeded)
What's Changed
New Contributors

Full Changelog: https://github.com/usestrix/strix/compare/v1.3.1...v1.4.0

View originalPermalink

v1.3.0

Changed 3
  • Reduce sandbox image size from 7.2GB to 3.8GB through cache cleanup, multi-stage Go build, and dropping ZAP
  • Polish local viewer UI and add Feedback & support tab
  • Add prominent scan switcher to local viewer and rename to pentest terminology
Fixed 2
  • Keep /app/.venv/bin on the login-shell PATH so python is accessible
  • Make root agent orchestrate-only and fold fixing into reporting
What's Changed

Full Changelog: https://github.com/usestrix/strix/compare/v1.2.0...v1.3.0

View originalPermalink

v1.2.0

Added 6
  • Resolve sandbox ports over a shared Docker network
  • Opt-in resource limits for docker sandbox containers
  • Recon asset discovery skill
  • Grafana Prometheus observability pivot skill
  • Local run viewer with email reports, run history, and the platform suite
  • Active Directory and Kerberos domain testing skill
Fixed 13
  • Stage symlink-safe copies for LocalDir uploads
  • Retry transient sandbox startup failures
  • Bound per-agent image memory with proactive budget and inherited-context scrub
  • Cap sandbox container logs to prevent host disk exhaustion
  • Close the docker client on session cleanup
  • Down-rate or skip findings on demo data and demo environments
What's Changed
New Contributors

Full Changelog: https://github.com/usestrix/strix/compare/v1.1.0...v1.2.0

View originalPermalink

v1.1.0

Added 14
  • Weak-password detection security skill
  • LLM prompt-injection security skill
  • GCP and Auth0 reconnaissance skills
  • Five new security skills for OAuth, AWS, prototype pollution, deserialization, and Django
  • Skill-directory registration
  • SARIF 2.1.0 emitter for GitHub code-scanning and ASPM ingestion
Changed 8
  • Use core LiteLLM dependency and cap openai<2.45 with litellm[proxy]
  • Require advisory_cvss for dependency findings with SCA TUI renderer
  • Omit SARIF version-control provenance for multi-repo scans
  • Attribute OpenRouter usage to the Strix app
  • Route ollama models through ollama_chat for tool calling support
  • Provider import-error hints for Bedrock and Vertex with full exception-chain walk
  • Environment variables win over persisted JSON across all aliases
  • Report cost for streamed OpenRouter calls
Fixed 9
  • Default sandbox exec commands to Bash so source works
  • Graceful stop with resume hint on persistent RateLimitError
  • Collapse child-agent initial input into a single user message
  • Atomic CSV and MD writes to prevent corruption on crash
  • Swallow torn-down docker socket on sandbox delete
  • Strip ANSI escapes and control bytes from terminal tool output

Strix v1.1.0

First release since v1.0.4. Highlights below (~56 merged PRs).

New security skills
  • Weak-password detection skill (#621, #654)
  • LLM prompt-injection skill (#616)
  • GCP and Auth0 reconnaissance skills
  • Five new skills: OAuth, AWS, prototype pollution, deserialization, Django (#617)
  • Skill-directory registration (#746)
SARIF / CI integration
  • SARIF 2.1.0 emitter for GitHub code-scanning / ASPM ingestion (#626)
  • STRIDE tagging of SARIF rules derived from CWE (#708)
  • Omit SARIF version-control provenance for multi-repo scans (#726)
Dependency / SCA reporting
  • New dependency reporting fields (#751)
  • Require advisory_cvss for dependency findings + SCA TUI renderer (#753)
Cost & scope controls
  • Configurable token / cost usage limits, --max-budget-usd (#576)
  • Bind-mount option for large target repos (#577)
  • --target list-file CLI option (#711)
LLM / provider
  • Use core LiteLLM dependency (#752); cap openai<2.45 + litellm[proxy] so fresh installs run (#748)
  • force_required_tool_choice setting (#730) and routed OpenAI required tool choice (#732)
  • Scan-agent tool registration (#733); root scan prompt options (#750)
  • Attribute OpenRouter usage to the Strix app (#760)
  • Warn when the configured LLM is not a recommended/frontier model (#586)
  • Route ollama models through ollama_chat so tool calling works (#562)
  • Report cost for streamed OpenRouter calls (#634)
Reliability / fixes
  • Default sandbox exec commands to Bash so source works (#764)
  • Provider import-error hints for Bedrock/Vertex, full exception-chain walk (#588)
  • Env vars win over persisted JSON across all aliases (#689)
  • Graceful stop with resume hint on persistent RateLimitError (#593)
  • Collapse child-agent initial input into a single user message (#589)
  • Atomic CSV/MD writes to prevent corruption on crash (#628, #631); csv_path indentation (#637); avoid note-ID collisions (#630)
  • Swallow torn-down docker socket on sandbox delete (#721); Caido HTTPS scheme (#722) + configured UI domains (#723)
  • Keep verbose openai.agents DEBUG off sandbox stdout (#704)
  • Strip ANSI escapes / control bytes from terminal tool output (#554)
TUI
  • Reduce scroll stutter via throttled refresh + render caching (#687)
  • "More content available" hint for long views (#687)
  • Restore snappy sweep/progress animation frame rate (#759)
CI / telemetry / chores
  • Lower Linux release glibc baseline (#707)
  • Deduplicate scan-ended telemetry (#758); minor telemetry updates (#761); drop unhandled-exception collection (#585)
  • Config-loader tests (#596); report-writer artifact tests (#667); uv.lock refresh (#606); README/docs updates
Contributors

Thanks to everyone who contributed to this release:

@0xallam @AtifAssari @Ayush7614 @Hardik-369 @Rome-1 @RudraDudhat2509 @Sonai124 @Stark-SK @ViperDroid @Zizouk22 @bastitva0-blip @bearsyankees @chirag127 @dpersek @e345ee @mhspektr @ousamabenyounes @sean-kim05 @seanturner83 @singe

View originalPermalink

v1.0.4

Changed 1
  • Make TUI quit instant by SIGKILL-ing the sandbox container
Fixed 3
  • Swallow sandbox container races in the stream consumer
  • Strip all images from session on vision-rejection, not just the latest
  • Strip ANSI escapes and control bytes from terminal tool output
What's Changed

Full Changelog: https://github.com/usestrix/strix/compare/v1.0.3...v1.0.4

View originalPermalink

v1.0.3

Changed 5
  • Simplify LLM configuration layer
  • Show "Send message to resume" on the left of the status bar
  • Gate Reasoning(effort=...) on registry support
  • Use observed LiteLLM cost for LiteLLM-routed calls
  • Simplify cost ledger to one bucket
Fixed 2
  • Fix SDK tracing leak and orphan docker on TUI quit
  • Gate reasoning_effort by LiteLLM model registry
What's Changed

Full Changelog: https://github.com/usestrix/strix/compare/v1.0.2...v1.0.3

View originalPermalink

More in AI

View all
codex

codex release notes.

codex
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

openclaw
superpowers

An agentic skills framework & software development methodology that works.

obra
ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

affaan-m
hermes-agent

The agent that grows with you

NousResearch
skills

Skills for Real Engineers. Straight from my .agents directory.

mattpocock

Discussion