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
- 126
#126
Policy gateway for AI agents: rule checks, human approval for risky actions, undo, and a tamper-evident audit trail.
GHHN#any-agent#claude-code#mcp-server2 posts · Sep 29★ 19
Stars:19
- 127
#127
Local-only secret manager (SOPS+age) with an MCP server so AI coding agents can inject secrets into commands without ever seeing the values.
GH#mcp-server#claude-code#codex1 post · Aug 17★ 15
Stars:15
- 128#128
BX is a macOS app that sandboxes AI coding tools and desktop apps using Apple's Seatbelt, with file rules, denied-access views and network c
HN#claude-code#codex#copilot1 post · Sep 8
no public repo
- 129
#129
A Claude Code plugin that audits Linux system hardening across 461 checks and produces a risk-ranked report without changing anything.
HN#claude-code#linux#cli1 post · Aug 12★ 14
Stars:14
- 130
#130
Open-source MCP control plane that time-locks agent write access until evidence, red-team review, and proof receipts pass.
GH#claude-code#cursor#vscode1 post · Aug 27★ 24
Stars:24
- 131
#131
Pure-Python CLI that statically scans MCP client configs for tool poisoning, rug pulls, hardcoded secrets, command injection and supply-chai
GH#cli#mcp-server#github-action1 post · Sep 26★ 544
Stars:544
- 132
#132
Security scanner for MCP servers, source trees, and packages, reporting findings and coverage gaps with pipeline gating.
GH#mcp-server#cli#linux1 post · Sep 26★ 31
Stars:31
- 133
#133
Dependency-free Python CLI that audits AI agent tool-call transcripts via hash-chain sealing, deterministic replay, and permission overreach
Stars:78
- 134
#134
Plants decoy MCP tools and canary tokens to detect prompt-injected coding agents and quarantine sessions via an SDK guard.
GH#claude-code#cursor#codex1 post · Sep 12★ 22
Stars:22
- 135
#135
A secrets vault that injects passwords and API keys into agent-run commands without exposing them, with guard hooks and skills for coding ag
GH#claude-code#cursor#codex1 post · Jul 21★ 71
Stars:71
- 136
#136
GitHub Action quality gate for AI-generated pull requests that blocks TODO leftovers, leaked secrets, sloppy commits and red CI before merge
GH#codex#claude-code#copilot1 post · Aug 20★ 136
Stars:136
- 137
#137
Hook-based supervision layer for Claude Code and Codex CLI that keeps an append-only ledger and blocks 'done' claims without a passing check
GH#claude-code#codex#cli1 post · Sep 11★ 122
Stars:122
- 138
#138
Security scanner that vets AI skills, MCP servers, and package trees in a sandboxed environment with multi-scanner findings and a triage das
GH#any-agent#mcp-server#docker1 post · Aug 1★ 12
Stars:12
- 139
#139
Runtime guardrails and adaptive authorization for AI coding agents: an MCP proxy and host hooks that give every tool call a PASS/AUTH/BLOCK
HN#claude-code#codex#cursor1 post · Aug 17★ 280
Stars:280
- 140
#140
Open-source local input scanner and firewall for AI agents: scans text, files and MCP traffic, blocks secrets and prompt injection via a Cla
HN#claude-code#mcp-server#github-action1 post · Jul 23★ 10
Stars:10
- 141
#141
Guardrail kit for coding agents: deterministic checks, a fresh-context reviewer that commits fixes, and one-way-door PR triage.
GH#claude-code#codex#opencode1 post · Sep 26★ 15
Stars:15
- 142
#142
Local skill router and prompt-injection firewall that routes only relevant skills, MCP servers and tools to AI coding agents per task.
GH#claude-code#codex#cursor1 post · Aug 24★ 17
Stars:17
- 143
#143
Kernel-layer runtime security for AI agents: per-agent file, exec, install and network policy enforcement with refusal audit logs.
GH#claude-code#codex#cursor1 post · Sep 21★ 11
Stars:11
- 144
#144
Screens AI agent tool calls and results via an MCP proxy and hooks, with policy thresholds, shadow mode, and audit logs.
GHHN#claude-code#any-agent#mcp-server2 posts · Sep 21★ 21
Stars:21
- 145
#145
CLI security scanner for AI agents and MCP servers with OWASP-mapped findings, Trust Card grades, SARIF output and CI gating.
GHHN#mcp-server#cli#github-action2 posts · Sep 9★ 13
Stars:13
- 146
#146
CLI that launches coding agents inside OS-native sandboxes with capability-scoped credentials, encrypted secrets, and statusline visibility.
HN#claude-code#codex#any-agent1 post · Sep 11★ 17
Stars:17
- 147
#147
Local privacy gateway that masks sensitive data in requests to LLM providers and restores it in streaming responses, for AI coding tools.
GH#claude-code#cursor#codex1 post · Sep 9★ 303
Stars:303
- 148
#148
Control plane for MCP tools agents run: inventory, evidence, policy and enforcement in CI and at runtime.
HN#mcp-server#cli#docker1 post · Oct 14★ 89
Stars:89
- 149
#149
Security hook for coding agents that risk-scores tool calls, flags prompt injection in results, and checks skills and instruction files.
GH#claude-code#codex#cursor1 post · Sep 17★ 153
Stars:153
- 150
#150
Exit-code tools and agent skills that catch test tampering, dead tests, and overfit fixes by AI coding agents.
GH#claude-code#codex#any-agent1 post · Aug 1★ 11
Stars:11