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
- 76#76
Windows app that adds a PreToolUse command guard and hash-chained audit record for Claude Code sessions via hooks and an MCP server.
HN#claude-code#windows#mcp-server1 post · Sep 1
no public repo
- 77
#77
Local MCP gateway with signed policies, one-time approvals and an evidence trail controlling which tool calls AI agents can run.
GH#mcp-server#any-agent#cli1 post · Sep 24★ 13
Stars:13
- 78
#78
A secure runtime for autonomous AI agents that enforces a constitution-derived policy on every tool call.
HN#claude-code#codex#docker1 post · Jul 14★ 612
Stars:612
- 79
#79
Security linter with 47 rules built around vulnerability patterns commonly produced by AI coding assistants, with CI mode and letter grades.
HN#cli#github-action#self-hosted3 posts · Sep 2★ 19
Stars:19
- 80
#80
DeepSeek Harness plugin that uses a second-model read-only reviewer subagent to auto-approve or deny agent tool requests, fail-closed with a
GH#plugin#any-model#deepseek1 post · Aug 13★ 234
Stars:234
- 81#81
Security scanner CLI that detects secrets, CVEs, and AI-specific code vulnerabilities and opens auto-fix GitHub PRs.
HN#claude-code#copilot#cursor1 post · Jul 14
no public repo
- 82
#82
Declarative allow/deny/ask permission rules plugin for DeepSeek Harness, gating coding-agent tool calls with audit logging and network polic
GH#plugin#any-model#any-agent1 post · Aug 13★ 122
Stars:122
- 83
#83
A local proxy that scans LLM requests and attachments for secrets, redacting or blocking them before they reach the model.
HN#any-agent#cli#self-hosted1 post · Sep 20★ 128
Stars:128
- 84
#84
Security scanner that pairs static taint analysis with your coding agent to dynamically verify or refute vulnerabilities in local apps.
GH#claude-code#codex#opencode1 post · Aug 19★ 137
Stars:137
- 85#85
Self-hosted Rust gateway that enforces budget caps, blocks runaway agent loops, and redacts credentials before dispatch to providers.
HN#any-agent#claude-code#codex1 post · Jul 20
- 86
#86
A harness for coding agents: guard hooks, rules, context modules, subagents and workflows, installed into Claude Code and ported to other cl
GH#claude-code#codex#gemini-cli1 post · Aug 18★ 22
Stars:22
- 87
#87
Open-source CLI security scanner that audits AI-written code, agent configs, MCP setups, secrets, and CI pipelines with evidence-backed find
HN#cli#mcp-server#any-agent1 post · Aug 6★ 858
Stars:858
- 88
#88
A Rust gate between AI coding agents and the shell that previews destructive commands, backs up before running, and enforces a readable poli
HN#claude-code#codex#cursor3 posts · Sep 29★ 27
Stars:27
- 89
#89
MCP server that blocks scope-creep, destructive, and prompt-injected tool calls from AI agents with ~25 µs overhead.
GH#mcp-server#any-agent#local-models1 post · Sep 4★ 12
Stars:12
- 90
#90
Open-source MCP gateway that checks agent tool calls against Cedar policies in a TEE and produces signed audit receipts.
HN#mcp-server#any-agent#cli1 post · Aug 4★ 33
Stars:33
- 91
#91
A write-time guard and CI gate that blocks LLM-induced code duplication, file bloat and doc drift, with no model in the loop.
GHHN#claude-code#mcp-server#plugin2 posts · Sep 8★ 21
Stars:21
- 92#92
Mac background app that detects secrets and PII in AI tool prompts and clipboard before they are sent, with local-only detection.
HN#claude-code#cursor#copilot1 post · Jul 16
no public repo
- 93
#93
Local CLI that runs checks and binds signed results to a git-state fingerprint, flagging STALE when code changes after an agent's test run.
GHHN#any-agent#cli#github-action2 posts · Aug 16★ 15
Stars:15
- 94
#94
Masks PII in prompts, files and tool output before it reaches AI models and restores it on screen, as a Claude Code plugin and Chrome extens
GH#claude-code#plugin#editor-extension1 post · Sep 18★ 21
Stars:21
- 95
#95
Local CLI and agent skill that stores API keys in the OS keychain and injects them into .env.local so coding agents never see key values.
GH#claude-code#codex#cursor1 post · Aug 23★ 17
Stars:17
- 96
#96
VS Code credential vault for SSH, VPN, databases and secrets with a broker so AI agents act on credentials without receiving them.
GH#vscode#any-agent#mcp-server1 post · Aug 23★ 13
Stars:13
- 97
#97
Local encrypted secrets vault for coding agents; agents reference secrets by name and values are injected and masked, never shown to the mod
HN#claude-code#codex#opencode1 post · Aug 29★ 86
Stars:86
- 98
#98
Open-source Python dependency scanner ranking exploited and unmaintained packages, with hooks that block coding agents from installing risky
GHHN#claude-code#codex#gemini-cli2 posts · Sep 19★ 24
Stars:24
- 99
#99
CLI that stores signed per-commit evidence records of agent-written code: line attribution, agent intent, and test results.
GHHN#claude-code#codex#opencode2 posts · Sep 13★ 23
Stars:23
- 100
#100
A security gate extension for the Pi coding agent that uses a probability model to judge and allow or block shell, write, and edit tool call
GHHN#pi#plugin#any-model2 posts · Sep 17★ 33
Stars:33