MySidoMySido
Sign In

TAG

#ai-safety

TEMPLATE

Councilof Ai (by CSOAI-ORG)

Council of AI — independent AI-behaviour measurement via GSPC. 305-leaf Merkle root, Bitcoin-anchored, Ed25519-signed. Open source.

TEMPLATE · 1 views

Prompt Engineering In Action (by Exponential-OS)

Co-Dialectic: catch your AI agreeing with you to please you, not because you're right. Sycophancy detection, cross-family judging, and prompt coaching that runs during the conversation rather than auditing after. Free and open source. Works with Claude, ChatGPT, Gemini.

TEMPLATE · 2 views

Ctrlrun (by CTRLRun)

The execution safety layer for AI agents.

TEMPLATE · 1 views

Impri (by sekera-radim)

Human-in-the-loop approval inbox for AI agents. An agent proposes an action, a human approves or rejects it, then it runs. Watchers + approval inbox, MCP + REST, self-hostable (MIT).

TEMPLATE · 2 views

Prime Directive (by djedi-knight)

One always-on duty-of-care rule for every AI coding agent — rendered into AGENTS.md, CLAUDE.md, Cursor, Windsurf, Cline, Copilot & Gemini files from a single source, verified by one command.

TEMPLATE · 1 views

Prime Directive (by 12529572-Canada-Inc)

One always-on duty-of-care rule for every AI coding agent — rendered into AGENTS.md, CLAUDE.md, Cursor, Windsurf, Cline, Copilot & Gemini files from a single source, verified by one command.

TEMPLATE · 1 views

Pkgdiet (by om-tajne)

Dependency policy and MCP server for AI-assisted JavaScript development. Stop AI coding agents from hallucinating deprecated npm packages.

TEMPLATE · 1 views

Palimpsest (by beepboop2025)

Open-source, revision-safe China economy observatory and verifiable AI/censorship measurement registry, with public data, MCP and offline verification.

TEMPLATE · 1 views

Webcite Mcp Server (by strategyconnect)

MCP server for fact-checking AI claims against authoritative sources. Works with any MCP-compatible agent — Claude, Cursor, Continue, Cody, Zed, Windsurf, OpenAI Agents, LangChain, and more.

TEMPLATE · 1 views

Data Agent Rules (by idk-arsh)

Rules, skills and a destructive-SQL seatbelt that keep AI coding agents (Claude Code, Codex, Cursor, Gemini CLI, Copilot) from scanning, overwriting or inventing data. With a 162-run DuckDB eval.

TEMPLATE · 1 views

Agent47 (by bmdhodl)

Python runtime checks for AI agents: budgets, loops, retries, and local traces. Zero runtime dependencies. MIT.

TEMPLATE · 2 views

MCPAudit (by saagpatel)

Audit all locally configured MCP servers for permission risks, prompt injection threats, and schema drift

TEMPLATE · 1 views

ThumbGate (by IgorGanapolsky)

ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

TEMPLATE · 1 views

Vitna Compliance Mcp (by COSTRINITY)

A containment layer for AI agents that go rogue. Guard mode wraps any stdio MCP server: calls to tools you mark as risky wait for a person, the agent can't approve its own hold, and claimed accounts get Ed25519-signed records you verify offline. Covers the servers you wrap. MIT c

TEMPLATE · 1 views

Deedglass (by deedglass)

An agent said it updated 1 row. Postgres changed 301. Deedglass checks what AI agents really did, enforces your rules, keeps signed records and has undo.

TEMPLATE · 2 views

Geiger (by sTeixeira83)

A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine

TEMPLATE · 1 views

Invinoveritas (by babyblueviper1)

The verification layer for autonomous agents — an independent, capital-aware verdict before an irreversible action (/review), a cryptographically signed proof after, and a public on-chain track record, losses included. Free EdgeProof backtest validation. Underneath: memory, sandb

TEMPLATE · 1 views

Telosignal Workflow Vault (by patrick-creates)

Documented n8n workflow templates (Google Sheets enrichment, invoice processing, Guardrails benchmark) plus an MCP server that critiques workflows.

TEMPLATE · 1 views

Privi Network (by canoydario847-cloud)

Privi: trust layer for AI agents. MCP servers for prompt-injection and data-leak checks (Privi Guard), MCP server safety grades (Privi Scan), tamper-evident audit logs, agent passports, spending mandates and a live kill switch. x402 USDC payments.

TEMPLATE · 1 views

Phantom Secrets (by ashlrai)

Stop AI coding agents from leaking your API keys. Local proxy + MCP that swaps real secrets for phm_ tokens — works with Claude Code, Cursor, Windsurf, and Codex.