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
64 tools, ranked by sources, chatter and star growth. How ranking works
- 01
#1
Offline Rust security scanner for MCP servers and AI agent tool extensions, with CLI, GitHub Action, VS Code extension, and runtime guard pr
HN#claude-code#cursor#any-agent3 posts · 3 days ago★ 21
Stars:21
- 02
#2
Desktop app that finds and revokes permissions, MCP servers, trusted folders and secrets granted to AI coding agents, with live alerts and h
HN#claude-code#codex#gemini-cli1 post · 7 days ago★ 15 +3/wk
Stars:15
+3 this week
- 03
#3
Static security scanner with 91 rules, an MCP server and agent skill that audits AI-written code for security flaws.
GHHN#claude-code#codex#cursor2 posts · 13 days ago★ 74 +41/wk
Stars:74
+41 this week
- 04
#4
Masks API keys, passwords and PII on your machine before coding agents see them, and restores real values in agent writes and commands.
HN#claude-code#codex#gemini-cli1 post · 11 days ago★ 13
Stars:13
- 05
#5
Local-first guardrails and context optimizer for coding agents: AST-based file slicing, secret-leak blocking, and token savings dashboards.
GH#claude-code#cursor#codex1 post · 13 days ago★ 47 +7/wk
Stars:47
+7 this week
- 06
#6
Local CLI that audits what coding agents can reach on your machine (secrets, risky modes, permissions) and applies one-command fixes.
GH#claude-code#codex#cursor1 post · 9 days ago★ 14
Stars:14
- 07#7
Guardrail that checks agent commands before they run, blocking destructive actions with local rules and an AI check, with a tamper-evident l
HN#claude-code#cursor#codex1 post · 11 days ago
no public repo
- 08
#8
Open-source daemon that discovers AI coding tools, inventories MCP servers and skills, applies sandbox policy, and connects devices to an LL
GHHN#claude-code#codex#cursor2 posts · 18 days ago★ 184 +10/wk
Stars:184
+10 this week
- 09
#9
CLI that scans recorded AI coding agent sessions for known secrets and guards future agent actions with hooks and provenance tracing.
GHHN#claude-code#codex#cursor6 posts · 16 days ago★ 254 +4/wk
Stars:254
+4 this week
- 10
#10
Open-source platform to manage, secure, and govern AI coding agents: MCP/LLM gateways, registries, hosted sessions, and audit logs.
HN#claude-code#codex#cursor1 post · Oct 21★ 1.2K +17/wk
Stars:1.2K
+17 this week
- 11
#11
Rootless container runtime and sandbox with no daemon that runs agent tool calls and LLM-generated code in kernel-enforced containers, with
GHHN#mcp-server#claude-code#cursor3 posts · Oct 16★ 493 +16/wk
Stars:493
+16 this week
- 12
#12
Open-source AI agent security platform: inventories coding agents, detects risky actions, and enforces guardrails at agent hooks.
GH#claude-code#codex#cursor1 post · 15 days ago★ 12 +1/wk
Stars:12
+1 this week
- 13
#13
Three agent skills that inventory, patch and test vulnerable PHP, Node.js and self-managed GitLab runtimes across repositories.
HN#claude-code#codex#cursor1 post · 27 days ago★ 14
Stars:14
- 14
#14
Open-source POPIA privacy guardrails: a skill for AI coding tools, a code scanner, compliance components and an MCP server.
GH#claude-code#cursor#codex1 post · Oct 18★ 14 +2/wk
Stars:14
+2 this week
- 15
#15
Skill that blocks AI reverse-engineering tools like REA via agent instruction barriers, terminal shims, and build hardening.
GH#claude-code#cursor#codex1 post · Oct 21★ 41 +1/wk
Stars:41
+1 this week
- 16
#16
Local guardrail that judges every AI coding agent tool call on-device with a small multilingual model and hooks into eleven agents.
HN#any-agent#local-models#cli1 post · Oct 13★ 40 +1/wk
Stars:40
+1 this week
- 17
#17
Local flight recorder for AI coding agents: records tool calls, detects credential exfil sequences, and forwards trails to a SIEM.
HN#claude-code#cursor#codex4 posts · Aug 2★ 47 +2/wk
Stars:47
+2 this week
- 18
#18
Local-first FinOps tool that prices coding agents' cloud commands before they run, blocks one-way doors, and tracks cloud and AI spend.
HN#claude-code#cursor#codex1 post · Jul 15★ 19
Stars:19
- 19
#19
Local, offline tool that records AI coding agents' file changes, reverts any of them, and alerts on secret reads and dangerous commands.
GH#claude-code#codex#cursor1 post · Jul 26★ 11
Stars:11
- 20
#20
Encrypted secret vault and MCP gateway that injects API credentials server-side so AI IDEs and agents never see raw keys.
GH#mcp-server#claude-code#cursor1 post · Jul 19★ 10
Stars:10
- 21
#21
Open-source policy engine and proxy that governs LLM, shell and MCP tool calls from coding agents with signed config and hash-chained audit
HN#claude-code#cursor#copilot1 post · Aug 28★ 32
Stars:32
- 22
#22
Uber's open-source security system for discovering, observing, and detecting threats from AI coding agents on enterprise endpoints.
HN#claude-code#cursor#codex1 post · Aug 6★ 2K
Stars:2K
- 23
#23
Zero-dependency Python web dashboard that visualizes Numbat's security findings about AI coding agent actions in real time.
GH#claude-code#codex#cursor1 post · Aug 8★ 16
Stars:16
- 24
#24
Repo of guardrails and 35 security Agent Skills plus a toolchain installer that turns AI coding agents into authorized security assistants.
GH#claude-code#cursor#codex1 post · Aug 8★ 11
Stars:11
- 25
#25
CLI that lints Agent Skills specs, audits unsafe instructions, and checks SKILL.md compatibility across coding agents.
GH#claude-code#cursor#codex1 post · Aug 13★ 12
Stars:12