Security scanner for AI agent tool definitions
GitHub repository with 16 stars and 6 forks.
Language: Go
Topics: ai-security, gateway, golang, mcp, model-context-protocol, prompt-injection, security-scanner, agent-safety, ai-security-tool, mcp-server
Trending score 0.06, activity score 0.11, stars gained +0, forks gained +0.
2026-06-13: 16 stars and 6 forks.
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
GitHub repository with 717 stars and 82 forks.
Trending score: 1.95; stars gained: +5; forks gained: +1.
Language: Go
Topics: agent-security, ai-agent-security, ai-agents, ai-firewall, ai-security, dlp
Prompt Gate — privacy-first, on-device DLP for the AI era. Blocks unauthorized AI tools at the DNS layer and inspects content sent to approved tools for secrets/PII, entirely on-device.
GitHub repository with 40 stars and 1 forks.
Trending score: 1.43; stars gained: +8; forks gained: +0.
Language: Go
Topics: ai-security, browser-extension, data-loss-prevention, dlp, endpoint-security, golang
A lightweight, highly secure AI API Gateway/Proxy written in Go. Acts as transparent middleware between local AI coding clients (OpenCode/Pi/Cursor) and upstream LLM providers (Gemini, DeepSeek, Zhipu z.ai).
GitHub repository with 17 stars and 0 forks.
Trending score: 1.03; stars gained: +4; forks gained: +0.
Language: Go
Topics: ai, ai-governance, ai-safety, ai-security, ai-tools, ai-gateway
Autonomous, read-only endpoint investigation via MCP. Ask a question about your fleet, get a narrative answer with containment recommendations.
GitHub repository with 21 stars and 1 forks.
Trending score: 0.61; stars gained: +1; forks gained: +0.
Language: Go
Topics: ai, ai-security, endpoint-security, golang, incident-response, mcp
Static analyzer for agent reliability.
GitHub repository with 19 stars and 4 forks.
Trending score: 0.60; stars gained: +1; forks gained: +0.
Language: Go
Topics: agent-security, agent-security-eval, agent-security-scanner, agent-security-tools, agent-tools, agents
Discover, govern and control access to MCP servers and agent skills across your organization
GitHub repository with 19 stars and 11 forks.
Trending score: 0.56; stars gained: +0; forks gained: +1.
Language: Go
Topics: ai, ai-governance, ai-security, golang, governance, mcp
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
GitHub repository with 21,758 stars and 1,302 forks.
Trending score: 5.89; stars gained: +730; forks gained: +44.
Language: Go
Topics: agent, agent-framework, ai-agent, ai-coding, cli, coding-agent
Local-first session intelligence and analytics for coding agents, supporting Claude Code, Codex, and more than 20 other agents. Also: 100x faster replacement for ccusage!
GitHub repository with 2,265 stars and 206 forks.
Trending score: 4.39; stars gained: +674; forks gained: +28.
Language: Go
Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
GitHub repository with 6,606 stars and 374 forks.
Trending score: 4.31; stars gained: +200; forks gained: +18.
Language: Go
Topics: agent, code-review, code-review-assistant, harness, repository-level-context
The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.
GitHub repository with 36,462 stars and 4,453 forks.
Trending score: 4.18; stars gained: +270; forks gained: +38.
Language: Go
Wrap Gemini CLI, Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.5, Grok 4.3, Claude model through API
GitHub repository with 37,416 stars and 6,172 forks.
Trending score: 4.15; stars gained: +242; forks gained: +28.
Language: Go
Topics: antigravity, claude-code, cluade, codex, gemini, openai
AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday. Built for Scrum teams where humans and AI agents collaborate as equals — on the same board, the same sprints, the same goals. Self-hosted. Fully customizable via config and plugins.
GitHub repository with 334 stars and 7 forks.
Trending score: 4.03; stars gained: +318; forks gained: +6.
Language: Go
Topics: ai-agent, bdd, clickup-alternative, jira-alternative, mcp, open-source
Sandbox any AI agent in seconds - zero setup, zero latency.
GitHub repository with 2,666 stars and 184 forks.
Trending score: 2.51; stars gained: +36; forks gained: +1.
Language: Rust
Topics: agent-sandbox, agent-security, ai-agent-sandbox, ai-agent-security, ai-agents, ai-security
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
GitHub repository with 717 stars and 82 forks.
Trending score: 1.95; stars gained: +5; forks gained: +1.
Language: Go
Topics: agent-security, ai-agent-security, ai-agents, ai-firewall, ai-security, dlp
Security-native LLM system for AI-generated application security.
GitHub repository with 261 stars and 71 forks.
Trending score: 1.44; stars gained: +1; forks gained: +0.
Language: Python
Topics: ai-security, appsec, code-security, llm, mcp, qlora
Prompt Gate — privacy-first, on-device DLP for the AI era. Blocks unauthorized AI tools at the DNS layer and inspects content sent to approved tools for secrets/PII, entirely on-device.
GitHub repository with 40 stars and 1 forks.
Trending score: 1.43; stars gained: +8; forks gained: +0.
Language: Go
Topics: ai-security, browser-extension, data-loss-prevention, dlp, endpoint-security, golang
Copy Fail (CVE-2026-31431): 9-year-old Linux kernel LPE found by Theori's Xint Code
GitHub repository with 3,926 stars and 876 forks.
Trending score: 1.30; stars gained: +2; forks gained: +1.
Language: Python
Topics: ai-security, cve-2026-31431, exploit, linux-kernel, privilege-escalation, privilege-escalation-exploits
Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net
GitHub repository with 67 stars and 19 forks.
Trending score: 1.13; stars gained: +2; forks gained: +0.
Language: TypeScript
Topics: ai-firewall, ai-safety, ai-security, application-security, ctf, guardrails