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

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

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

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.

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

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

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

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

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.