Updated daily · last run Nov 20, 07:02 UTC
Trending in the bucket
Every AI dev tool the internet posted about, ranked by who's talking about it. Sorted. Mostly.
- In the bucket
- 3.1K
- Posts read
- 42.7K
- Tossed out
- 33.7K
186 tools, ranked by sources, chatter and star growth. How ranking works
- 101
#101
dsh plugin that uses the Jev non-generative model to classify tool-call risk, gate auto-approval, and score session message retention.
GH#plugin#any-model1 post · Sep 22★ 32
Stars:32
- 102
#102
Mac app that stores API/SSH credentials in an encrypted vault and runs authenticated actions for AI agents over MCP, keeping keys out of age
GH#claude-code#mcp-server#macos1 post · Jul 14★ 193
Stars:193
- 103
#103
Runtime permission firewall for AI agents: YAML policies, popup/Telegram approvals, and tamper-evident signed audit logs.
GH#claude-code#opencode#any-agent1 post · Sep 22★ 10
Stars:10
- 104
#104
CLI that discovers and scans installed agents, MCP servers, and skills for prompt injections, malware, and other security risks.
HN#claude-code#cursor#codex1 post · Aug 30★ 3.1K
Stars:3.1K
- 105#105
Open-source deterministic guardrail engine that blocks prompt-injection data exfiltration in AI agent tool calls without breaking agents.
HN#any-agent#self-hosted#cli1 post · Sep 28
- 106
#106
An unofficial OpenCode plugin that reviews every 'ask' permission request with a tool-free AI model against a tenant policy, allowing, denyi
GH#opencode#plugin#any-model1 post · Aug 4★ 16
Stars:16
- 107#107
Local sandbox that runs LLM-generated code in fresh, rootless, no-network containers with labelled fault verdicts, plus an MCP server and La
HN#mcp-server#cli#linux1 post · Sep 28
- 108
#108
MCP server plugin for Cursor that scans AI-agent codebases and MCP servers for risky patterns, scores production readiness, and writes SARIF
GH#cursor#mcp-server#any-agent1 post · Aug 11★ 24
Stars:24
- 109
#109
CLI that runs coding agents through a multi-role pipeline (implementer, reviewer, QA) in isolated worktrees, enforcing protected paths, pre-
GH#claude-code#codex#gemini-cli2 posts · Sep 26★ 12
Stars:12
- 110
#110
Security layer for AI coding agents that records agent actions and enforces YAML policies before they run.
HN#claude-code#any-agent#cli1 post · Aug 30★ 176
Stars:176
- 111
#111
Docker sandbox that runs Claude Code CLI against one project folder while keeping the rest of the host machine invisible to the container.
Stars:44
- 112
#112
Docker integration for Decionis, a deterministic policy gate that authorizes AI agent actions with human approval and signed decision dossie
GH#any-agent#mcp-server#docker1 post · Aug 18★ 165
Stars:165
- 113
#113
Locally masks personal data in documents before they are sent to an LLM and restores originals in the response, working as a Claude Code ski
GH#claude-code#any-agent#local-models1 post · Aug 18★ 20
Stars:20
- 114
#114
Plugin collection that auto-approves harmless shell permission requests in coding agents using probabilistic AI judgments.
GH#claude-code#opencode#plugin1 post · Sep 18★ 30
Stars:30
- 115
#115
Privacy monitor for AI coding tools that logs snapshots, flags sensitive file access and credential leaks, and can block Git history archivi
Stars:14
- 116
#116
Guardrail hooks and a plan-implement-verify-review command loop for Claude Code, blocking risky git and SQL commands.
GH#claude-code#codex#plugin1 post · Aug 31★ 45
Stars:45
- 117
#117
Runtime constraints for the pi coding agent: checks every side-effecting tool call against user-stated rules before it runs.
Stars:13
- 118
#118
A CLI that gives coding agents fast calibrated judgments (safety checks, triage, diff review, ranking) from TypeSafe's Jev model, installabl
GH#cli#any-agent1 post · Sep 16★ 49
Stars:49
- 119
#119
Policy and approval layer that intercepts destructive or expensive coding-agent actions and records signed decision ledgers.
HN#claude-code#codex#cli2 posts · Sep 7★ 312
Stars:312
- 120
#120
Static security scanner for AI agent skills, SKILL.md files and MCP configs that flags dangerous instructions without executing them.
GH#claude-code#codex#cursor1 post · Aug 16★ 64
Stars:64
- 121
#121
Secrets management for AI agents: approve API keys and credentials on your phone with biometrics, delivered end-to-end encrypted into the ta
GH#claude-code#codex#cursor1 post · Sep 16★ 11
Stars:11
- 122
#122
AI-powered secret scanner for code and git history that pairs entropy detection with LLM adjudication, runs as a CLI, pre-commit hook, GitHu
GH#claude-code#cli#mcp-server1 post · Aug 6★ 11
Stars:11
- 123
#123
Local fail-closed policy enforcement, secret redaction, and human approval for MCP tool calls across coding agent hosts.
GH#claude-code#codex#cursor1 post · Aug 17★ 100
Stars:100
- 124
#124
A skill that audits installed agent skills for trigger wording, token cost, and shipped executable code.
GH#claude-code#any-agent#plugin1 post · Aug 19★ 16
Stars:16
- 125
#125
Open-source runtime that rules on every AI coding agent tool call (allow, ask, deny) before it runs, enforcing policies, code fingerprints a
GH#claude-code#codex#cursor1 post · Aug 10★ 11
Stars:11