OpenACA – security scanner for AI agent stacks (MCPs,skills,plugins)
SCA for agent configs when Snyk and Dependabot can't read mcp.json files.
An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.
AI that builds its own ClickHouse instance and extends itself with Discord.
Developers, teams wanting persistent AI workers
Cognition Devin · Adept AI
SCA for agent configs when Snyk and Dependabot can't read mcp.json files.
Bulk-install AI skills across 30+ agents from one terminal UI.
Waitlist-only infrastructure wrapper for OpenClaw with no novel tech.
eBay-scraping agent sources hardware for a Mac mini datacenter running agents 24/7.
Forage proxies MCP capability discovery so an agent can search registries, install a package as a child process, emit list_changed so the agent picks the tool up immediately, and even write usage notes to CLAUDE.md for future sessions. That operational pattern — dynamic install + instant availability + persisted learnings — is a clever, pragmatic fix for brittle agent setups, though the project is clearly early and raises real security/trust questions around auto-installing third-party MCPs (user approval is noted but sandboxing/attestation will matter).
Retool and Appsmith already solve internal tools with larger ecosystems.