Senthex AI firewall for LLM API calls (one line of code, 16ms overhead)
Heuristic-based shields beat LLM-in-the-loop detectors on speed, but Lakera Guard already owns this space.
Wire-protocol circuit breaker for agents when LangSmith costs too much.
Developers running multi-agent systems (CrewAI, AutoGen, LangGraph)
LangSmith · Helicone · Portkey
Anyone running multi-agent setups (CrewAI, AutoGen, LangGraph) knows the pain: agents go rogue, tokens burn, no circuit breaker.
Building an open-source Go reverse proxy. Change one env var (OPENAI_BASE_URL=http://localhost:8080/v1), it detects death spirals and physically cuts the connection.
Local-only, no SDK, no cloud, single binary. Ship in 2 weeks if enough people need it.
Have you been burned by runaway agents?
Heuristic-based shields beat LLM-in-the-loop detectors on speed, but Lakera Guard already owns this space.
Fixes truncated JSON on the wire in ~10µs without SDK changes or retries.
Lyapunov stability theory for LLM loops beats hard budget caps any day.
Hard budget kill-switch stops runaway agent costs before the bill hits.
Lyapunov stability theory catches token spirals before your budget explodes.
Agent cost killswitch solves a real pain, but monitoring infra is crowded.