1,400 tools found
Promptfoo example testing Claude Fable 5 on hard coding tasks - debugging, concurrency-aware generation, and security review.
Office Open XML Viewer renders DOCX, XLSX, and PPTX to a Canvas in-browser via Rust/WASM parsers, entirely AI-built.
Lathe generates hands-on multi-part tutorials you work through yourself, with opt-in step verification and source provenance.
Multi-step prompt workflow that migrates legacy codebases using sandbox agents to isolate shell commands and file edits while keeping orchestration
Promptfoo example that authenticates Anthropic Messages API evals via a local Claude Code OAuth session, not a separate API key.
Promptfoo example wiring Claude to an MCP server via the Anthropic Messages provider, auto-executing tool calls.
Lightweight CLI that filters verbose command output and file content before it reaches your AI agent, cutting token usage.
AI code review CLI from Alibaba that reviews diffs or whole files with line-level precision, using about 1/9 the tokens of general agents.
Open-source Claude Code harness for autonomous vulnerability discovery, verification, and patching of C/C++ memory bugs via ASAN and gVisor sandboxing.
Local-first memory sidecar that builds a persistent knowledge graph from LLM conversations and injects scored context into prompts.
Self-hosted, open-source harness for multi-user, multi-agent teams - config-based access control instead of prompt-based rules.
Self-hosted daemon running Claude Code, Codex, Copilot, OpenCode, and Pi agents in parallel, controllable from phone, desktop, or CLI.
