Инструменты

CLI and library for evaluating and red-teaming LLM apps: compare prompts and model outputs in bulk, scan for security vulnerabilities and plug into CI/CD, with evals running locally. Now part of OpenAI and still open source under MIT.

Open-source reverse engineering framework and CLI: disassemble, debug, emulate and patch binaries across many architectures and file formats, scriptable through r2pipe or built-in JavaScript.

Encrypts secret values in YAML, JSON, ENV and INI config files using AWS, GCP or Azure KMS, age or PGP, so secrets can be safely committed to Git alongside code. A CNCF sandbox project.

Google's official skill library and plugin marketplace: nearly 150 skills focused on Google Cloud (GKE, BigQuery, Cloud Run, IAM and more), plus 17 product plugins pairing skills with MCP for Cloud SQL, Spanner, AlloyDB, BigQuery, GCS and others.

Google's official skill library, focused on Google Cloud: 100+ skills for gcloud, Cloud Run, GKE, BigQuery, IAM, monitoring and logging, and the Well-Architected Framework, plus Ads and Analytics.

Industrial-grade open-source speech recognition toolkit from Alibaba's ModelScope, with an agent-friendly funasr command that turns audio into text, JSON or SRT subtitles in one step, with speaker diarization and timestamps. Strong on Chinese. Requires PyTorch.

AI2's tool for converting PDFs and scans to Markdown with a vision LLM, handling equations, tables, handwriting and multi-column layouts, suited to bulk digitizing papers and archives. Local runs need an NVIDIA GPU with 12GB+ VRAM; otherwise use a paid OpenAI-compatible remote endpoint.

Browser control from the browser-use team: an editable CDP connection lets agents drive the Chrome you are already using, writing missing helper functions as they go and keeping them for reuse. Also offers an MCP server. Allow remote debugging in Chrome on first use.

Lets Claude Code push ML research forward unattended: literature review, topic selection, experiment deployment, cross-model review loops and paper writing through rebuttal, in 80+ skills. Codex acts as the independent reviewer by default; other model pairings work too.

Context and harness engineering skills covering context compression and optimization, multi-agent architectures, memory systems, tool design and LLM-as-judge evaluation, activated automatically by task. Aimed at building production-grade agent systems.

Context and harness engineering skills: context fundamentals, degradation diagnosis and compression, multi-agent architectures, memory systems, tool design, LLM-as-judge evaluation and self-improvement loops. Focused on principles and design patterns, not tied to any agent platform.

Semantic multi-language static analysis: find vulnerabilities and bugs with rules that look like source code, across 30+ languages with custom rules. Scans locally by default without uploading code; cross-file analysis and Pro rules require sign-in.

Semgrep's official MCP server, now part of the main semgrep repo and started with semgrep mcp: lets agents run static security scans, find issues with custom rules and inspect syntax trees. Requires the Semgrep CLI; connecting to the AppSec platform needs SEMGREP_APP_TOKEN.

Helps support teams categorize and prioritize tickets, emails or chat logs and suggest next steps; drafts replies, organizes repro steps and reminds you to redact customer data before sharing. Works with exports from Zendesk, Intercom and others or pasted chats; no account or API key needed.

ModelScope's official training framework for LLMs and multimodal models: the swift command covers pretraining, fine-tuning, RL, inference, evaluation, quantization and deployment for 600+ text and 400+ multimodal models, with Megatron parallelism and a web UI. Usually needs a GPU.

Version datasets and models the way Git versions code: data lives in remote storage like S3 or GCS while versions are tracked in your Git repo. Also offers reproducible pipelines and local experiment tracking, rerunning only the steps affected by a change.

Open-source zero-shot TTS via f5-tts_infer-cli: from a few seconds of reference audio it reads Chinese or English text in the same voice, handy for lessons and videos. Needs Python, PyTorch and FFmpeg, ideally a GPU. Pretrained models are non-commercial; get consent before cloning a voice.

Writes precise prompts for a specific AI tool: identifies the target tool, extracts your intent, asks at most three questions if details are missing, then outputs a lean, paste-ready prompt. Covers dozens of tools including ChatGPT, Claude Code, Cursor, Midjourney and Sora.

Turns 18 kinds of sources, including doc sites, GitHub repos, PDFs and videos, into skill packages for Claude and other platforms, or exports RAG chunks and vector store data. Optional MCP server, and it can call a local agent like Claude Code to enrich content. Needs Python 3.10+.

Security baseline and compliance checks for AWS, Azure, GCP, Kubernetes, GitHub, M365 and more, with built-in CIS, NIST, PCI-DSS, SOC 2 and other frameworks. Generates reports or opens a local dashboard. Configure credentials for each cloud account first.

Plugin marketplace for AI research with nearly 100 skills in 23 categories, from ideation, fine-tuning and post-training to distributed training, inference serving, evaluation and paper writing, coordinated end to end by the autoresearch skill.

Nearly 100 skills spanning the AI research workflow: ideation and literature review, fine-tuning and post-training, distributed training, inference serving, evaluation, interpretability and paper writing, tied together by an autoresearch orchestration skill.

Classic network discovery and security auditing tool: host discovery, port scanning, service version and OS detection, plus vulnerability checks with NSE scripts. Only scan networks you are authorized to test.

Wraps 150+ security tools such as nmap, sqlmap and nuclei for agents to orchestrate, covering network recon, web pentesting, binary analysis and CTFs. Clone the repo, install the tools yourself and start the local server. For authorized testing only.