Releases

Slack integration for systemprompt.io. Verifies Slack Events API, slash-command, and Block Kit interaction requests, maps Slack users to governed systemprompt identities, and dispatches to A2A agents under the same RBAC and audit pipeline as every other inbound surface.

Internal component of hotl - no semver promise; pin exact or don't depend. L3 turn engine, M0 slice: sample→tools loop, max_turns, cancellation.

Microsoft Teams integration for systemprompt.io. Validates Azure Bot Service activity tokens, maps Teams users to governed systemprompt identities, and dispatches to A2A agents under the same RBAC and audit pipeline as every other inbound surface.

Schema-aware, storage-backed application persistence layer for MongrelDB with migrations, relational constraints, and a query builder.

Hand-rolled single-threaded TLS 1.3

CLI for counting lines of code per language

Procedural macros used by hubuum_client to define Hubuum API resources.

Safe, idiomatic Rust bindings for GTCaca, a libcaca-based terminal UI toolkit

Agent-to-Agent (A2A) protocol for systemprompt.io AI governance: streaming, JSON-RPC models, task lifecycle, .well-known discovery, and governed agent orchestration.

Provider-agnostic LLM integration for systemprompt.io AI governance — Anthropic, OpenAI, Gemini, and local models unified behind one governed pipeline with cost tracking and audit.

A library for interacting with Deepwoken data in a more convenient format, with a few added utilities.

High performance, spec-compliant Fast Lightweight Online Encryption (FLOE) implementation

Template registry, loading, and rendering for systemprompt.io config-as-code AI governance deployments. Handlebars-powered template engine for the MCP governance pipeline.

Raw FFI bindings to GTCaca, a libcaca-based terminal UI toolkit

Native Model Context Protocol (MCP) implementation for systemprompt.io. Orchestration, per-server OAuth2, RBAC middleware, and tool-call governance — the core of the AI governance pipeline.

Marketplace bounded context for systemprompt.io. Resolves the active marketplace, loads the on-disk catalogue (plugins, skills, agents, hooks, managed MCP servers), scopes and per-user filters it, and assembles the canonical signed bridge manifest.

Markdown content management, sources, and event tracking for systemprompt.io AI governance dashboards. Governed publishing pipeline for the MCP governance platform.

Analytics for systemprompt.io AI governance infrastructure. Session, agent, tool, and microdollar-precision cost attribution across the MCP governance pipeline.

Core, language-neutral model for MongrelDB Kit: schema, key encoding, validation, constraint planning, migration planning, and query AST.

OAuth 2.0 / OIDC with PKCE, token introspection, and audience/issuer validation for systemprompt.io AI governance infrastructure. WebAuthn and JWT auth for the MCP governance pipeline.

Shared utilities and provider-agnostic streaming chat (ChatProvider, OllamaProvider, OpenRouter, tool-use) for trusty-* projects

File storage, metadata, and access control for systemprompt.io AI governance infrastructure. Governed file operations for the MCP governance pipeline.

DataFusion sqllogictest driver

User management for systemprompt.io AI governance infrastructure. 6-tier RBAC, sessions, IP bans, and role-scoped access control for the MCP governance pipeline.

Cloud API client, credentials, OAuth, and tenant management for systemprompt.io AI governance deployments. Remote sync and multi-tenant orchestration for the MCP governance pipeline.

File and module discovery infrastructure for systemprompt.io AI governance — manifests, schemas, and extension loading. Separates I/O from shared models in the MCP governance pipeline.

CLI for counting lines of code per language

Security infrastructure for systemprompt.io AI governance: JWT, OAuth2 token extraction, scope enforcement, ChaCha20-Poly1305 secret encryption, the four-layer tool-call governance pipeline, and the unified authz decision plane (deny-overrides resolver + AuthzDecisionHook) shared by gateway and MCP enforcement.

Evidence-backed temporal memory for personal agents

Internal component of hotl - no semver promise; pin exact or don't depend. L6 context assembly, M0 slice: owner system prompt, AGENTS.md in the untrusted envelope, byte-stable prefix.