Specialized LLM for clinical workflows trained via a human-gated self-evolution loop to improve patient consultation, multimodal clinical reasoning, interactive diagnosis, and EHR tool use. Iteratively refines targeted synthetic and curated data based on benchmark failures to raise specific capabilities without broad regressions.
Provides a unified tool catalog and proxy for AI agents: one team token lets agents call thousands of third-party endpoints (and your team’s keys) with per-call pricing. Injects credentials server‑side so agents never hold provider secrets, and exposes CLI/skill recipes and OAuth tools for team-wide use.
Keeps AI development agents working across sessions, with persistent memory, task checkpoints, and scheduled jobs. Runs on your own hardware and is accessible through desktop, web, CLI, and messaging channels.
Converts completed on-policy trajectories into natural-language 'hindsight skills' and converts the skill-induced action probability shifts into a dense token-level on-policy distillation signal, jointly optimized with outcome-based RL to improve sample efficiency and long-horizon agent behavior.
Provides 50 ARC‑AGI‑3 gameplay trajectories (GPT‑5.6 Sol and Claude Opus/Fable) plus a dependency‑free scorer and event logs; includes sanitized session data, snapshots, and utilities to recompute RHAE scores for reproducible agent evaluation and cross-model comparison.
Turns fragile, implicit search progress into explicit, persistent, shared state for multi-agent information seeking — externalizes progress as Frontier Task, Evidence Graph, Coverage Map and Failure Memory, and uses pipeline-parallel scheduling plus a middleware harness to avoid repeated failed searches and improve utilization and throughput.
Guides an LLM agent to build persistent, editable DAG-based data pipelines via typed, incremental mutations instead of free-form scripts. Combines DataFlow-Skills, a Model Context Protocol exposing live operator registry and pipeline state, and a synchronized Web UI; achieves 93.3% end-to-end pass rate on a 12-task benchmark while cutting cost and latency versus script baselines.
Provides verified, model-attested end-to-end agent coding and debugging trajectories (JSONL). Each whole-session trace was produced by moonshotai/kimi-k3 on the pi/openrouter runtime, passed acceptance tests and independent model screening — useful for SFT, distillation, and analyzing tool-use behavior.
Models long-horizon interactive literary simulation where characters and world co-evolve; introduces an open‑schema framework with a Character Agent and an LLM-based World Model, plus seven trainable tasks and a dataset from 57 books for benchmarking persistent narrative state.
Provides newline-delimited JSON agent session traces (5 files) generated with Teich for moonshotai/kimi-k3, including recovered and embedded tool-schema snapshots so traces remain training-ready even when tools weren't invoked; includes guidance for Teich data preparation and conversion.
Turns Claude Code or Codex into an agent skill that storyboards, animates, and sound-designs cinematic product promos from your real screenshots using Remotion. Packs tuned shot recipe cards, 150+ motion previews, a production-ready template, Remotion components, and audio assets for web/desktop product films.
Provides under-1K JSON agent-trace records documenting model refusal responses and forensic metadata — useful for evaluating refusal-detection, audit pipelines, and safety analysis; small size limits large-scale statistical studies.