68,124 packages matching “action-kernel”
@qmilab/lodestar-adapter-git
v0.5.0 · 1 month ago
Git status tool adapter for the Lodestar Action Kernel. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@qmilab/lodestar-adapter-filesystem
v0.5.0 · 1 month ago
Filesystem adapter for the Lodestar Action Kernel: governed reads and root-confined writes. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@qmilab/lodestar-adapter-shell
v0.5.0 · 1 month ago
Governed shell-command tool adapter for the Lodestar Action Kernel. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@qmilab/lodestar-adapter-nostr
v0.5.0 · 1 month ago
Governed Nostr transport tool adapter (publish/fetch) for the Lodestar Action Kernel. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@qmilab/lodestar-adapter-http
v0.5.0 · 1 month ago
Governed HTTP transport tool adapter (fetch/request) for the Lodestar Action Kernel. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@qmilab/lodestar-adapter-messaging
v0.5.0 · 1 month ago
Governed messaging egress tool adapter (Slack/email) for the Lodestar Action Kernel. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@kavtuai/guildgate
v1.1.1 · 1 day ago
Guarded action kernel and security, realtime, storage, operations, and analytics infrastructure for Discord dashboards.
No known vulnerabilities
@qmilab/lodestar-guard
v0.5.0 · 1 month ago
The write-side trust layer — wrap an agent loop and route every tool call through the Action Kernel, every observation through the Cognitive Core. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@qmilab/lodestar-adapter-sql
v0.5.0 · 1 month ago
Governed SQL/database tool adapter (parameterized-only query + mutation) for the Lodestar Action Kernel. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@qmilab/lodestar-runtime-core
v0.5.0 · 1 month ago
The language-agnostic governance-gate sidecar — govern a non-MCP agent runtime (LangGraph, CrewAI, AutoGen) by remoting each native tool call through the Action Kernel over a thin NDJSON-RPC seam. The reusable spine of Lodestar's runtime-adapter epic.
No known vulnerabilities
@qmilab/lodestar-guard-mcp
v0.5.0 · 1 month ago
MCP proxy mode for Lodestar Guard — wrap any MCP-speaking agent (Claude Code, Cursor, Aider) so every tool call passes through the Action Kernel and every result through the Cognitive Core. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@qmilab/lodestar-adapter-vector
v0.5.0 · 1 month ago
Governed Vector/RAG retrieval tool adapter (pgvector similarity search; retrieved chunks are external_document) for the Lodestar Action Kernel. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@qmilab/lodestar-action-kernel
v0.5.0 · 1 month ago
Tool registry, two-phase action execution, and sandbox profiles for the Lodestar epistemic chain. Part of Lodestar, the trust layer for AI agents.
No known vulnerabilities
@red-codes/kernel
v2.9.3 · 4 months ago
Governed action kernel for AgentGuard
No known vulnerabilities
@onkernel/sdk
v0.86.0 · 1 day ago
The official TypeScript library for the Kernel API
No known vulnerabilities
@textlint/types
v15.8.0 · 4 days ago
Type definition package for textlint
No known vulnerabilities
ml-kernel
v4.0.0 · 2 months ago
A factory for kernel functions
No known vulnerabilities
@textlint/kernel
v15.8.0 · 4 days ago
textlint kernel is core logic by pure JavaScript.
No known vulnerabilities
ml-kernel-polynomial
v3.0.0 · 2 months ago
The polynomial kernel
No known vulnerabilities
@stdlib/math-base-special-kernel-cos
v0.2.4 · 6 months ago
Compute the cosine of a double-precision floating-point number on [-π/4, π/4].
No known vulnerabilities