Search

SANDAL - Safe Agentic Natural-language Database Access Layer. Production-grade agentic database assistant CLI using LangGraph and LLMs (Google Gemini, OpenAI, Anthropic)

Sergent Python reference implementation: async model transport with adapters for OpenAI, Anthropic, Gemini, and Ollama

Ultra-fast n8n PostgreSQL suite with Redis L1 caching: Database Node, AI Agent Tool (usableAsTool), and Tiered Chat Memory with native n8n credentials.

Governed, structure-aware retrieval and execution planning for agentic systems.

Local message bus between terminal coding agents: Claude Code, Codex, Muse, OpenCode, Pi, Cursor

Single Node Activated Inference Layer — a Python DSL for composing frozen neural primitives into typed dataflow programs.

GitHub Copilot CLI for @sigx/ai-agent — the Copilot CLI as an Agent on the official @github/copilot-sdk: sessions, streaming, permissions through your policy, in-process client tools, a switchable model list

Core of ai-agent-context: repository knowledge graph, architecture detection, incremental scanning, deterministic .agent/ serialization. Local-first, zero runtime dependencies, no LLM required.

Git-native context layer for AI coding agents: scan a repository into a structured, versionable .agent/ knowledge layer and query it (CLI + programmatic API).

One headless turn of a coding agent (Claude Code or Codex): launch, run, read, classify.

Agentic API gateway for OpenAI-compatible inference servers

Create a production-ready Agents24 React application.

Multi-tenant, fail-closed Sphinx RAG extension for the doxtr ecosystem (dual-store ChromaDB knowledge base with security-classified xlinks).

Per-turn skill selection for LangChain and LangGraph agents: a judge picks the loadout, the catalog stays out of the prompt.

Bound what a compromised LLM agent can reach and do

Local-dev MCP sidecar for exposing selected Hermes Agent capabilities.

Interactive CLI helper to boot up the Ultimate FastAPI + LangChain AI Agent Boilerplate framework.

n8n community node for K2 Horizon (IFM) — a chat model for the AI Agent plus a node for direct calls, with native tool calling, reasoning effort and structured output

Record real agent-harness API traffic, replay it byte-for-byte against LLM providers, compare cache behaviour and cost

GoDaddy provider for LangChain & LangGraph — Agent Identity (registration, discovery, verification)