Provider-neutral System One runtime for TypeScript and Pi
Build production AI agent runtimes in Rust with typed tools, provider-neutral LLM adapters, streaming, storage, and observability.
Portable contracts and local-first runtimes for canonical data, retrieval, durable execution, and agent-facing AI.
Operating layer for durable AI work — mandates, evidence and human decisions across replaceable AI execution.
Provider-neutral LLM router and model orchestration engine with auto-learning and budget zones
Open-source reference architecture and template for provider-neutral AI-native game studio workflows.
Java middleware framework for cache, messaging, jobs, and governance extensions.
Provider-neutral skill pipeline (Claude, GitHub Copilot/GPT, OpenAI Codex) for autonomous plan -> build -> review -> ship: 57 skills (54 portable with three adapters each, 3 Claude-native), calibrated judges, and install/build/release tooling.
Provider-neutral durable orchestration runtime for approval-gated multi-agent work
Provider-neutral autonomous ML research paper writer — ideation -> LaTeX writeup -> peer review -> anti-hallucination numerical audit. Spun out from hermes-sci to remove Hermes-runtime coupling.
Policy-aware model execution with portable routing, budgets, fallbacks, and receipts
Provider-neutral Supabase database adapter exposing typed CRUD, schema management, and realtime subscriptions.
Portable, provider-neutral model invocation contracts, adapters, and conformance tools
Legend State adapter for provider-neutral StateAdapter contracts.
Provider-neutral operating standard and reusable assets for AI-assisted collaboration projects
Provider-neutral MCP server for software engineering: requirements, goals, milestones, portable implementation plans, verification and durable handover for coding agents, backed by SQLite.
Governed, provider-neutral LLM gateway for deterministic model authorization, explainable routing, safe fallback, provenance, and policy-enforced execution.
Small, opt-in .NET libraries for the shared technical concerns repeated across the local application portfolio: identity, billing, tenants, jobs, storage, caching, eventing, mailing, and AI.
A hybrid testing runner for AI agents: write high-level plans for fresh code, execute deterministic steps directly, and use LLMs only where runtime interpretation is needed.
A local-first, provider-neutral platform for secure and observable AI agent workloads.
To associate your repository with the provider-neutral topic, visit your repo's landing page and select "manage topics."