Search

No description available

No description available

Evaluation harness — scenario × model matrix, deterministic / LLM judges, `pass^k` reliability summaries, and JSON/Markdown reports. Includes the `agent-engine-eval` CLI. Runtime-optional; for release gates and model selection.

PostgreSQL-backed long-term `MemoryManager` — scoped retrieval, provenance, and supersede/tombstone lifecycle — through a host-injected pg-compatible client.

On-device / small / local raw-text model `Planner`. Inject a `TextGenerator` (Ollama / llama.cpp / transformers); all weak-model resilience — tolerant JSON parsing, repair retries, plan-then-execute, self-consistency voting, verifiers — lives inside. Incl

Remote-model `Planner` adapter — turns an `AgentContext` snapshot into an OpenAI Responses API request and validates the result as a structured `Action`.

TellMesh — URI-first agent monorepo umbrella (uri3, nl2uri, hypervisor, agent factory)

Drop-in MLflow tracing for omnigent agents

Offline, deterministic data-lineage documentation for SQL + Power BI estates: Markdown for LLM agents, searchable dark-mode HTML for humans.

Spring AI multilingual customer-service Agent platform for cross-border ecommerce, with RAG, order tools, escalation, and Vue admin UI.

Terminal coding agent that executes tools (real think>tool>result loop with confirm + undo, MCP tools in-loop) and rewrites its own system prompt from feedback with metrics + auto-rollback. Free by default via the FCM model router.

The web wrangler for agents. Give your AI a real browser and never touch the web yourself again.

🐻 직구곰 — Amazon US→네이버 스마트스토어 무재고 구매대행 자동화. 돈=결정론 파이프라인, 판단=멀티에이전트(평가/콘텐츠/CS). FastAPI+Next.js 어드민. pytest 115.

Meta-agent and runtime client for TellMesh hypervisor

A PostgreSQL-first starter generator for coding agents.

Mimir persistent memory tool for CrewAI agents

Run any agent (Claude, Codex, custom) on any machine — with no API key on the machine. A secure, self-hosted proxy for models and tools.

Coordination certificate for multi-agent (LangGraph) systems: prove your agent graph is deterministic, deadlock-free, loop-aware, optimally scheduled, and retry-safe — static analysis, CI-ready.

Run Claude Code-style subagents across your local model fleet.

Kalmia Tracing SDK — automatic LLM call tracing for OpenAI and Anthropic