Tag

Ling-2.6-1T

A trillion-parameter LLM optimized for long-context, low-latency text generation and agentic coding workflows. Combines MLA+Linear Attention and a post-training 'fast thinking' token-suppression strategy to reduce token overhead and improve multi-step execution reliability for production agents.

Orkas

Turns ongoing goals into delegated work, coordinating built-in specialists and local CLI agents across a persistent project. Conversations, files, and project memory stay on your computer by default.

Converts technical books and document collections into an on-demand agent “skill” that Claude Code, GitHub Copilot CLI, and Amp can load to answer questions from the original content. Produces a compact SKILL.md plus per-chapter files so agents load only the needed sections, cutting token use and reducing hallucination risk.

χ-Bench

Evaluates LLM-driven agents on long-horizon, policy-rich U.S. healthcare workflows using 75 clinical task fixtures and a 20-app MCP simulator; includes task fixtures, shared worlds, and leaderboard integration (Managed-Care handbook is gated).

Knowledge Catalog

Provides tools and samples to build context management, enrichment, and retrieval solutions on Google Cloud Knowledge Catalog — an AI-oriented data catalog that builds a dynamic knowledge graph for structured and unstructured data, suitable for RAG and agent workflows.

Inferact/codex_swebenchpro_traces

Provides JSON traces from a Codex-driven swebenchpro agentic benchmark, including per-call token counts, cache hit rates, timing, and per-trial outcomes. Useful for research into LLM caching, long-context workloads, and agent evaluation. MIT-licensed and compact.

Multi-Benchmark LLM Agent Traces

Provides 1,781 OpenTelemetry execution traces of LLM-powered agents across six benchmarks, including full conversations, token usage, timing, tool calls and model metadata—useful for performance analysis, agent-behavior research, and inference debugging.

Ring-2.6-1T

A trillion-parameter reasoning model aimed at long-horizon, multi-step agent workflows and tool collaboration. Offers adjustable Reasoning Effort modes (high, xhigh), async RL training (IcePop), and very long context (128K→256K) for complex production scenarios.

Centaur

Runs shared, self-hosted AI agents in isolated Kubernetes sandboxes accessible from Slack or an API. Provides durable workflows, reusable tool plugins, and network-edge credential injection (iron-proxy) so agents can execute real work securely and audibly for teams.

DataPrep-Bench: Benchmarking LLMs as Training Data Preparators

Measures how well LLMs and agent-driven workflows prepare supervised training data end-to-end by jointly benchmarking data construction and data-quality evaluation across six domains, using a downstream-grounded protocol and new metrics.

Kun

Local-first AI agent workspace that unifies coding, writing, design, research and automation under one runtime shared between a desktop GUI and a terminal TUI. Features Agent Graph for long-running, auditable workflows, multi-provider model support, and local-by-default data storage.

Nakama

Runs and manages AI agents for teams, with isolated organizations, per-agent permissions and memory, and access through a web dashboard, messaging channels, and external apps.