Six in-process middlewares for OpenClaw: HITL approvals, prompt-injection guardrails, PII redaction, tool-call budgets, context compaction, and complexity-aware model routing. Zero telemetry, all state local.
GitHub repository with 10 stars and 0 forks.
Language: TypeScript
Topics: ai-guardrails, ai-safety, context-compaction, human-in-the-loop, llm-agents, llm-observability, middleware, model-routing, openclaw, pii-redaction
Trending score 0.09, activity score 0.36, stars gained +0, forks gained +0.
2026-06-05: 10 stars and 0 forks.
Six in-process middlewares for OpenClaw: HITL approvals, prompt-injection guardrails, PII redaction, tool-call budgets, context compaction, and complexity-aware model routing. Zero telemetry, all state local.
GitHub repository with 10 stars and 0 forks.
Trending score: 0.09; stars gained: +0; forks gained: +0.
Language: TypeScript
Topics: ai-guardrails, ai-safety, context-compaction, human-in-the-loop, llm-agents, llm-observability
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.
GitHub repository with 59,229 stars and 6,667 forks.
Trending score: 5.98; stars gained: +1,178; forks gained: +117.
Language: TypeScript
Topics: agent-skills, ai-agents, ai-design, byok, claude-code-for-design, claude-design
Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
GitHub repository with 41,875 stars and 2,580 forks.
Trending score: 5.83; stars gained: +2,953; forks gained: +188.
Language: TypeScript
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
GitHub repository with 10,655 stars and 892 forks.
Trending score: 4.82; stars gained: +560; forks gained: +62.
Language: TypeScript
Topics: ai-agent, ai-coding-agent, anthropic, bun, claude, cli
The API to search, scrape, and interact with the web at scale. 🔥
GitHub repository with 128,932 stars and 7,675 forks.
Trending score: 4.80; stars gained: +954; forks gained: +49.
Language: TypeScript
Topics: ai, crawler, markdown, scraper, html-to-markdown, llm
🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning swarm intelligence, RAG integration, and native Claude Code / Codex Integration
GitHub repository with 57,954 stars and 6,626 forks.
Trending score: 4.76; stars gained: +401; forks gained: +52.
Language: TypeScript
Topics: claude-code, swarm, agentic-ai, agentic-framework, agentic-rag, agentic-workflow
Write HTML. Render video. Built for agents.
GitHub repository with 24,557 stars and 2,290 forks.
Trending score: 4.72; stars gained: +732; forks gained: +60.
Language: TypeScript
Topics: ai, animation, ffmpeg, framework, gsap, html
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.
GitHub repository with 71 stars and 10 forks.
Trending score: 0.31; stars gained: +1; forks gained: +0.
Language: Python
Topics: ai-agents, ai-guardrails, ai-safety, anthropic, async, content-moderation
Six in-process middlewares for OpenClaw: HITL approvals, prompt-injection guardrails, PII redaction, tool-call budgets, context compaction, and complexity-aware model routing. Zero telemetry, all state local.
GitHub repository with 10 stars and 0 forks.
Trending score: 0.09; stars gained: +0; forks gained: +0.
Language: TypeScript
Topics: ai-guardrails, ai-safety, context-compaction, human-in-the-loop, llm-agents, llm-observability
Local guardrails for AI coding agents. Wraps any MCP server and blocks destructive tool calls — DROP TABLE, rm -rf, force-push, unscoped UPDATE/DELETE — before they execute. Free, open-source, runs entirely on your machine.
GitHub repository with 5 stars and 0 forks.
Trending score: 0.02; stars gained: +0; forks gained: +0.
Language: Rust
Topics: ai-coding-agents, ai-guardrails, ai-safety, claude-code, cline-ai, continue