v0.2.0 · MIT License
Enables watching the skills and MCP servers an agent depends on, retrieving version history and diffs, and discovering what to chain next.
v0.9.0 · MIT License
Stores what AI agents learn — thoughts, decisions, session events and repo facts — in PostgreSQL with pgvector and serves it back through versioned MCP tools with hybrid vector-plus-full-text retrieval and budgeted context packs. Enables multiple agents to share one scoped, role-isolated long-term memory, with deliberate promotion of distilled candidates into durable memories.
v1.0.0 · MIT License
Exposes the battle.training agent tank arena API as MCP tools, letting clients read ladder standings, bot ratings, recent matches and replay URLs, and inspect cup info. With an API key it also enables registering bots, uploading smoke-tested controller versions, and enrolling in sponsored cups.
v0.2.0 · MIT License
Enables agents to analyze OpenAPI contracts for deterministic integration risks, plan auth, sync, action, and webhook candidates, and diff contract versions for likely breaking changes through read-only tools.
v1.0.0 · MIT License
Checks public IPs, domains, CVE IDs and software versions for confirmed vulnerabilities and exposure, using NVD version ranges, CISA KEV, EPSS, distro backports and published exploits. All API keys are optional.
v1.0.0 · GPL 3.0
Enables AI assistants to design coffee brew profiles from bag photos, push them to a Wi-Fi-connected smart brewer, and keep a searchable library of recipes, versions, ratings, gear and tastings. Also lets assistants manage the brewer's active menu and scheduled brews, and preview, import or share brew.link profiles.
v0.1.0 · MIT License
Enables read-only MCP access to structured Brazilian curricular references, supporting learning-objective searches, comparisons across states, and queries tied to versioned publications.
v0.1.0 · MIT License
Enables agents to look up a library's Context7-compatible ID and fetch its current, version-specific documentation and code examples, optionally focused on a topic and capped at a chosen token budget.
— · Apache 2.0
A local Python + SQLite MCP memory service that stores persona, shared experiences, facts, agreements, and unfinished work, then restores them within a context budget so a new model can continue the same conversation. It supports offline original-text persistence, Chinese keyword retrieval, provenance-tracked memories, persona versioning/rollback, and progressive fading of older events.