Legion
AI agents that act inside your Elixir app by writing sandboxed Lua
Emerged finds new products worth a look, daily — what’s new today
Tessary
Screens every agent trace cheaply, then sends a stronger model after bad ones
If you only grade a sample of your agent's traces, this checks all of them and comes back with likely causes instead of a dashboard of scores.
An open-source reliability layer for production AI agents. Traces arrive over OTLP using the gen_ai conventions, PII is redacted, and light classifiers sweep every one. An LLM triage step drops false alarms, related findings become cases, and an agentic root-cause pass reads the failing traces and, if connected, your repo. It explains and routes; it does not write fixes. Self-host with Docker Compose under Apache-2.0, or use the free cloud. Co-founded by Akhil.
More like this
Fanout
Self-hosted traces, logs and metrics that you and your agents can query
OtoDock
Self-hosted company OS that runs Claude Code and Codex agents as staff
Isle
Managed desktop environments for computer-use agents, with checkpoints
Geiger
Inventory every AI agent on your machine and what it can reach
SpecWeave 3
Spec-first scaffolding so one coding agent can resume another agent's task