Search

Agent harness that turns natural-language intent and on-screen selection into verified changesets — pluggable model provider, knowledge, and strategy. Output is a changeset or nothing.

MeridianOS — provider/harness-agnostic autonomous agent-orchestration core with cost governance. npx meridian-gateway in 60s.

A structured production readiness and code quality workflow Agent Skill for AI coding assistants to catch common vibe-coded configuration issues.

Render CLI LaTeX and read Markdown with images directly in the terminal.

Terminal proxy that intercepts AI agent shell commands and requires human confirmation before destructive operations

Local, free voice artifacts for AI agents

Two-stage retrieval + gating long-term memory engine for coding agents.

Always-on containerized dev environment for AI coding agents, driven over SSH+tmux.

Deterministic AI Agent Trajectory Evaluation Engine — Zero judge-LLM cost, zero non-determinism, instant execution.

MultiGrid Sports: Research-grade multi-agent gridworld environments for reproducible RL experiments

Contamination-resistant A-share backtesting, evaluation, and trajectory generation for autonomous LLM trading agents

Test Fetch.ai uAgents without a network, a wallet, or a sleep().

Run Mistral Agents (Conversations API) on Flyte.

Shared contract for Flyte agent-SDK adapters.

Run Google ADK (Agent Development Kit) agents on Flyte.

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...