Showing 1-12 of 57
Use CortexBrain to add lightweight observability to distributed AI agents. Start the repo's local example, add basic metrics, import the dashboard, and spot issues fast.
Sitrep is an open-source AI incident copilot that watches your screen, deduplicates tiles, and links screenshots to Grafana traces/logs for evidence-backed answers. Demo ~2 hrs.
A 3-hour plan for small teams to add an inspectable sandbox between product and model endpoints, with rollout gates, test targets, and risk tiers informed by the Open Secure AI Alliance.
Step-by-step: clone and run Palmier Pro on macOS, connect a local MCP AI agent (Claude/Codex), and run a 120-minute trial edit to reduce export/import cycles.
60–90 minute guide to deploy OneCLI, an open-source gateway that proxies agent requests, enforces host/path policies, and injects scoped credentials so agents never see raw keys.
Run Yorishiro locally to give coding agents a 3D presence that visibly signals states — including immediate reactions to build failures — by editing small JavaScript packs.
Orka is an open-source pre-execution checkpoint that vets agent actions (allow/deny/confirm) to stop runaway loops, limit costs, and create an auditable record.
Moonshot AI says its 2.8T Kimi K3 will be open-sourced on 27 July — possibly the first openly downloadable ~3T model. It arrives after US regulators briefly forced Anthropic withdrawals.
A compact how-to to run PokeTokenBar locally. This open-source demo maps AI token counts to Pokémon-style states, letting small teams visualize usage without exposing raw billing.
Hands-on guide to adding a stateful AI agent to Flutter apps with memex-lab/dart_agent_core. Learn planning, tool use, streaming partial outputs and sub-agent delegation.
Hands-on checklist to run a ChatbotX developer instance, configure a minimal lead-capture flow (greet → contact → webhook), test integrations, and review production readiness.
Step-by-step guide to clone and run brendenehlers/diplomacy-ai demos, save reproducible logs, collect move histories, and compare agent configs to measure behavior.