AgentDish directory
Top Picks
The listings that cleared review with the strongest evidence.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
|
#1153
↓ -3
Daimon
Local privacy gateway that redacts sensitive text before sending prompts to external LLMs, then reconstructs the final answer locally. |
Developer Tools / Code Assistant | 83 | ↓ -3 | 20 days ago | Details |
|
#1154
↓ -3
Ante
Ante is a self-contained coding agent that runs in your terminal, supports local models, and offers CLI, TUI, server, and gateway modes. The page highlights public benchmarks, low resource usage, and support for multiple providers and agent orchestration. |
Developer Tools / Code Assistant | 83 | ↓ -3 | 21 days ago | Details |
|
#1155
↓ -3
dsh-edge
An open-source project that deploys a persistent DeepSeek-based coding agent on Cloudflare Workers with one-command installation and durable workspace support. |
Developer Tools / AI Coding Agents | 83 | ↓ -3 | 21 days ago | Details |
|
#1156
↓ -3
Syndicate OS
Self-hosted multi-agent federation for running Hermes agents and OpenClaw minions with a board, tender market, memory layers, and decision provenance. |
Developer Tools / Code Assistant | 83 | ↓ -3 | 22 days ago | Details |
|
#1157
↓ -3
Seedstr
Seedstr is an AI fundraising assistant that analyzes a founder’s deck, model, and data room to rank seed investors and suggest who to approach, how to contact them, and when. |
Sales / Lead Generation | 83 | ↓ -3 | 23 days ago | Details |
|
#1158
↓ -3
Sentrint
Sentrint is a security scanner for apps built with LLM platforms like Bolt, Cursor, and v0. It scans repos for secrets, access rules, vulnerable dependencies, and risky code paths, then returns plain-English findings and a copy-paste fix prompt. |
Security / Code Security | 83 | ↓ -3 | 23 days ago | Details |
|
#1159
↓ -3
Kungfu
Open-source tooling for keeping coding-agent work alive across sessions and handoffs. It preserves work state, evidence, and next steps across agents like Codex, Claude, OpenCode, and Amp, with a CLI and local workspace flow. |
Developer Tools / AI Agent Infrastructure | 83 | ↓ -3 | 27 days ago | Details |
|
#1160
↓ -3
agent-guard
A lightweight shell-based guard that blocks destructive commands before an AI coding agent can run them. It targets risky actions like git reset --hard, rm -rf, force-pushes, and destructive cloud/database commands, with local regex rules and a test script. |
Developer Tools / AI Agent Safety | 83 | ↓ -3 | 27 days ago | Details |
|
#1161
↓ -3
e3d-pilot
A repo-improving agent harness that researches a codebase, proposes ideas, waits for human approval, and then drives execution with SHA-bound merge gating. |
Developer Tools / AI Agent Frameworks | 83 | ↓ -3 | 28 days ago | Details |
|
#1162
↓ -3
mcp-uplift
A CLI bridge that wraps legacy MCP stdio servers so they can run behind the newer stateless 2026-07-28 protocol. The page includes a concrete usage example, client configuration snippets, compatibility behavior, and known limitations. |
Developer Tools / Protocol Adapter | 83 | ↓ -3 | 30 days ago | Details |
|
#1163
↓ -3
Proxima
An out-of-tree vLLM plugin that compresses KV cache with STAR-KV to fit more concurrent requests and longer contexts on the same GPU memory budget. |
Developer Tool / LLM Serving / vLLM | 83 | ↓ -3 | 31 days ago | Details |
|
#1164
↓ -3
Hallucinote
Hallucinote is an AI-assisted music authoring tool for Ableton Live that turns prompts into editable song projects, with round-trip sync, review, and branchable iterations. |
Music / AI music production | 83 | ↓ -3 | 31 days ago | Details |
|
#1165
↓ -3
evidence-verify
A Go/Python tool for verifying AI audit logs, checking chain integrity, tamper detection, and whether a log is independently anchored outside the producing system. |
Developer Tools / AI Compliance / Audit Logging | 83 | ↓ -3 | 34 days ago | Details |
|
#1166
↓ -3
Revise MCP Server
MCP server that connects external AI agents to Revise for drafting, editing, reading, exporting, and sharing DOCX-compatible documents with tracked changes. |
AI Writing / Document Editing | 83 | ↓ -3 | 35 days ago | Details |
|
#1167
↓ -3
laikacms/decap-cms
A Git-based CMS for static site generators, packaged as a pnpm workspace with install, build, test, and demo instructions, plus documentation for usage and configuration. |
Developer Tools / CMS | 83 | ↓ -3 | 36 days ago | Details |
|
#1168
↓ -3
ARF — a record format for evaluation runs
ARF defines a JSON record format for AI evaluation runs with canonicalization and reproducible SHA-256 digests, so scores can be traced back to the underlying question, model, inputs, and judgment. |
Developer Tool / AI Evaluation / Data Format | 83 | ↓ -3 | 36 days ago | Details |
|
#1169
↓ -3
Agents Never Sleep
A small macOS menu bar app that keeps your Mac awake so long-running AI agents can continue running with the lid closed. |
Productivity / Mac utility | 83 | ↓ -3 | 37 days ago | Details |
|
#1170
↓ -3
Nodes
A native macOS markdown writing app for plain .md notes on your own disk, with on-device AI search and semantic lookup. |
Productivity / Writing | 83 | ↓ -3 | 37 days ago | Details |
|
#1171
↓ -3
RequestGuard
RequestGuard creates CAPTCHA-gated short links that hide the destination until a visitor passes verification. It also supports expiry, passwords, and an API/SDK for generating protected links from a backend or embed flow. |
Developer Tools / API | 83 | ↓ -3 | 37 days ago | Details |
|
#1172
↓ -3
mcpvessel
A CLI for running untrusted MCP servers in sandboxed containers with deny-by-default egress, traffic watching, and host approval workflows. It can also compose servers into agents and expose them over OCI registries. |
Developer Tools / Security / Sandboxing | 83 | ↓ -3 | 38 days ago | Details |
|
#1173
↓ -3
Vale-LLM-slop
A Vale style pack that lints prose for AI-like writing, inspired by ASD-STE100. It helps teams catch buzzwords, vague phrasing, self-praise, and other patterns in docs, comments, and agent-authored text. |
Writing / Copywriting | 83 | ↓ -3 | 39 days ago | Details |
|
#1174
↓ -3
Capshelf
A Git-backed CLI for sharing agent skills, settings, and MCP fragments across repositories with per-project lockfiles and update workflows. |
Developer Tools / CLI / DevOps | 83 | ↓ -3 | 39 days ago | Details |
|
#1175
↓ -3
Authoryze
Authoryze is an MCP-native payment layer for AI agents that issues single-use virtual cards for approved purchases and adds spending limits, merchant rules, approvals, and audit trails. |
Developer Tools / API | 83 | ↓ -3 | 40 days ago | Details |
|
#1176
↓ -3
Claude Accounts
A paid desktop utility that launches separate, isolated Claude desktop app windows for multiple accounts on macOS and Windows. |
Developer Tools / Desktop Automation | 83 | ↓ -3 | 41 days ago | Details |