open-core

Open-Sourcing the integration engine our platform runs on

Self-hosted family office engine: typed Python calculators, a private SQLite ledger, and specialist agents for Claude Code and Codex. Agents propose. Typed code computes.

Discrete inference, calibration, sensitivity, and reviewed early BidKing reference code.

Learning how to make a RISC-V

General Purpose 8 Qubit Optical Quantum Computer

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.

Enterprise Agent Operating System — AI employees that learn your business and deliver outcomes. Self-hosted, open core.

57-tool supervised Meta Ads MCP server for Claude Code. Open-core: full CRUD, multi-asset ads, targeting, diagnostics, safety gates. Premium adds 41 tools: optimization engine, vault intelligence, copy generation.

mirror of https://git.elphel.com/Elphel/eddr3

mirror of https://git.elphel.com/Elphel/x393

Open-source Instagram comment-to-DM automation and campaign OS for agencies, powered by Meta Graph API, Next.js, Prisma, Redis, BullMQ, and Stripe.

mirror of https://git.elphel.com/Elphel/x393_sata

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human approval, execute-once gateway, tamper-evident receipts. Open core, Apache-2.0.

Deterministic wavelet-scattering features for physics. Open control plane (AGPL); GPU engine distributed as binaries. Nothing learned, nothing leaked.

Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in safety, async follow-ups, and native compliance

inplan — a Markdown editor for human ⇄ coding-agent planning. CLI + desktop editor.

Open-core HR API — self-hostable leave, attendance, people, and org management with fine-grained access control. Bun + Hono + Drizzle + OpenFGA.

A video-call avatar frontend for your local LLM agent (Hermes/OpenClaw) — replaces the messenger chat and serves the agent's exact slash-command menu. Open-core engine: emotion, mood, voice, build-your-own-avatar pipeline. GPU-free · MIT.

Self-hosted Dakera AI memory server — Docker Compose, Kubernetes, Helm, HA cluster setup, and monitoring.

Remote-control Claude Code, Codex, and other AI coding agents from your phone. Stream your terminal AI session to a native Android app — no USB, no port forwarding, no LAN required.