Agents

Multi-agent orchestration for DeepSeek Harness. Sessions in one workspace assign work, review results, and run DAG workflows — without you as the messenger.

One-command installer for pythia: PL/SQL development for AI agents on Oracle Database. Installs the Python CLI, the skill pack, and the .pythia/ config scaffold.

Local A2A gateway for waking AI agent runtimes

Local execution agent for ysagc: a state-agnostic, safety-bounded worker that connects to a platform backend over WebSocket, executes tool instructions inside an authorization root, and reports results back.

Run Pipa through Slack Socket Mode with OpenCode

First-Person Agent Memory Bench. 10 Categories including fact recall, multi-hop links, temporal reasoning, fact overwrites, speaker traps, refusal, credibility, and agentic tool usage. 540K token / 60 session corpus, all in first person. Dynamic output-answer-key portion. Comprehensive report with visuals and miss breakdown.

A durable execution runtime for LLM agent workflows.

Run Claude Code headlessly as a local inference layer: named experts, multi-turn sessions, bounded concurrency.

dbt-native Snowflake Cortex Agent materialization with skill and evaluation tooling