npm · crates.io
endojs/endo
Endo is a distributed secure JavaScript sandbox, based on SES
Apache-2.0Sep 15, 2026 · metrics 2.10.0
All tags
Catalogue tag
#capabilities
Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.
21 records
crates.io
microsoft/wassette
Wassette: A security-oriented runtime that runs WebAssembly Components via MCP
MITSep 13, 2026 · metrics 2.10.0
npm · PyPI
QVerisAI/qveris-agent-toolkit
Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs for agents to discover, inspect, call, and audit real-world tools.
MITSep 9, 2026 · metrics 2.10.0
Packagist
browscap/browscap-php
Officially supported Browscap for PHP
MITSep 17, 2026 · metrics 2.10.0
PyPI
Alien6-Studio/outerspace-apizr
Open-source capability compiler for Python codebases: static discovery, typed contracts, REST/MCP interfaces and governed execution.
GPL-3.0Oct 11, 2026 · metrics 2.10.0
PyPI
geopython/OWSLib
OWSLib is a Python package for client programming with Open Geospatial Consortium (OGC) web service (hence OWS) interface standards, and their related content models.
BSD-3-ClauseSep 17, 2026 · metrics 2.10.0
crates.io
Kirky-X/trait-kit
Lightweight Rust module interface standard — centralized capability registry, dependency injection, and configuration management without heavy DI frameworks
Custom licenseSep 25, 2026 · metrics 2.10.0
PyPI · npm
SamoTech/skills-tree
The universal, platform-agnostic skills and capability registry for AI agents — mapping capabilities, skills, implementations, dependencies, evidence, and platform adapters across agent ecosystems.
MITOct 4, 2026 · metrics 2.10.0
npm
infragate/capa
One capabilities.yaml wires skills, tools, rules, sub-agents, MCP servers, and plugins into Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and 30+ other AI coding agents
No licenseSep 14, 2026 · metrics 2.10.0
npm
baabakk/llm-ports
TypeScript LLM Abstraction Layer for Multi-Provider AI Systems. Multi-provider routing, fallback chains, USD cost gating, capability factories, tool-use security.
MITSep 15, 2026 · metrics 2.10.0
npm
0xsarwagya/ontoly
Open-source Software Intelligence Platform. Deterministic verification, structural PR reviews, interactive graph explorer, and proactive intelligence — powered by the Software Graph. 41 node types · 32 relationships · 120+ checks.
AGPL-3.0Sep 13, 2026 · metrics 2.10.0
Packagist
anilcancakir/laravel-ai-sdk-skills
A skill system for Laravel AI SDK agents. Define reusable AI capabilities with SKILL.md files.
MITSep 15, 2026 · metrics 2.10.0
crates.io
lucab/caps-rs
A pure-Rust library to work with Linux capabilities
Custom licenseAug 27, 2026 · metrics 2.10.0
PyPI
ZlaylowZ/modelroster
Accurate, current LLM model identifiers and capabilities for every provider — shipped as data, refreshed from official sources.
MITOct 16, 2026 · metrics 2.10.0
crates.io
ikigai-rs/ikigai-core
The ikigai resource-resolution kernel: address information by identity, resolve through composable spaces, cache once. Runtime-free; compiles to WebAssembly.
Apache-2.0Oct 12, 2026 · metrics 2.10.0
Packagist
getmilpa/resolver
Milpa Resolver — resolve the architecture before booting it: contracts, capabilities, surfaces and host profiles into a learnable ResolutionReport. Apache-2.0.
Apache-2.0Sep 18, 2026 · metrics 2.10.0
npm
haex-space/haex-ucan
UCAN-based capability tokens for haex space authorization
No licenseSep 24, 2026 · metrics 2.10.0
npm
DebadityaHait/skillcap-lock
Review what an Agent Skill can newly do, not just what bytes changed
MITSep 18, 2026 · metrics 2.10.0
PyPI · crates.io
nonameuserd/paybond-kit-python
Python SDK for agent spend governance around paid tool calls across MCP, LangGraph, OpenAI, Claude, and Gemini: spend authorization, evidence receipts, refunds, disputes, and settlement.
Apache-2.0Sep 15, 2026 · metrics 2.10.0
npm
nonameuserd/paybond-kit
TypeScript SDK for agent spend governance around paid tool calls across MCP, LangGraph, OpenAI, Claude, and Gemini: spend authorization, evidence receipts, refunds, disputes, and settlement.
Apache-2.0Sep 13, 2026 · metrics 2.10.0
PyPI
iagop03/antcrew-engine
Capability-driven autonomous project execution engine. Iterates an Operator loop over a goal, dispatching modular capabilities (Architect, CodeGenerator, TestRunner, BugFixer, etc.) until the project reaches a desired artifact state. No LangGraph dependency — designed as a standalone Layer 2 that antcrew (Layer 1) builds on top of.
No licenseAug 14, 2026 · metrics 2.10.0