Routes code-based AI agents through repeatable reverse-engineering and pentesting workflows and orchestrates local and remote tools (jadx, Frida, IDA, BurpSuite) so agents can triage APKs, binaries, JS, firmware, and CTFs without guessing the toolchain. Includes master routing rules, tool-index detection, MCP integration, and a field-journal for reusable lessons.
Self-hosted CPA / CLIProxyAPI management and observability panel that stores request history, tracks cost/usage/quota, and centralizes provider/credential/OAuth and plugin management. Designed for local analytics, failure diagnosis and account automation without telemetry.
Node-based infinite-canvas web workstation for iterative visual creation — integrates image/video generation, reference editing, prompt library, multi-agent assistants, and asset management. Runs in-browser with configurable OpenAI-compatible endpoints; suited for local/personal deployment (AGPL-3.0).
Provides long-term memory for AI coding agents by compiling sanitized lifecycle observations into a git-versioned Markdown wiki that enables cross-agent handoffs, per-project isolation, and optional vector-backed retrieval.
Runs a multi-stage, Claude-powered pipeline to find, verify, triage, and generate patches for code vulnerabilities, plus interactive skills for threat modeling and customization. Default harness targets C/C++ memory bugs using ASAN inside Docker/gVisor; autonomous runs execute target code and require sandboxing.
Agentic LLM for long-horizon, environment-driven workflows: decomposes goals, generates and executes code/tool calls, evaluates outputs, and iterates. The Pro variant emphasizes coding and terminal execution and is published for use with sglang and multi-node H100 deployment.
Provides a virtual, durable filesystem and pluggable execution runtimes for agents running inside Cloudflare Durable Objects. Offers container, isolate-shell, and isolate-JS backends; preview-stage API with ~10GB Durable Object backing and FUSE-mounted container trade-offs.
Multilingual, low-latency text-to-speech model for speech generation and zero-shot voice cloning. Uses an MoE backbone with ECAPA-TDNN speaker embeddings, supports audio prefixes, fine-grained prosody/emotion controls and 44.1kHz output; optimized for Linux + NVIDIA GPUs.
Self‑hosted A‑share quantitative workbench for screening, monitoring, backtesting and stock-level analysis using TickFlow data; supports 18 Polars strategies, vectorbt backtesting, realtime rule-based alerts, pluginable data sources and optional LLM-driven strategy generation and stock analysis.
Measures how autonomous AI agents learn via long-horizon, feedback-rich executable tasks; publishes 51 public tasks from a 134-task suite and provides SForge, a two-container evaluation harness for iterative 12+ hour runs to track learning trajectories.
Evaluates proactive, multimodal agents on 400 bilingual real‑world tasks across five capability axes (Skill Usage, Exploration, Long‑Context Reasoning, Multimodal Understanding, Cross‑Platform Coordination) using live Docker‑based, stepwise closed‑loop evaluation to separate base model skills from framework design.
Provides 37,484 validated command-line tasks generated by recursive task synthesis, each paired with searchable metadata and a sanitized, runnable package (instructions, solution, verifier, and optional Dockerfile).