Skip to recent updates
Insights / Updates Review evidence health Next best action: Open the highest-priority queue
Freshness Desk

Recently updated agents and stale candidates

Freshness desk for recently updated AgentStaffer listings, stale watchlists, update dates, and profile/trust links. Use re-review for governance decisions.

Use updates for

Freshness discovery

Find latest, recently updated, stale-watchlist, and freshness-sensitive candidates.

Use re-review for

Lifecycle decisions

Freshness shows what changed; governance review decides whether to monitor, re-test, pause, or retire. Open governance queue.

Freshness BucketsBucket counts and freshness boundaries stay available here.
4938Updated in 180 days
35Active this year
14Aging source
13Stale source
Recent UpdatesLatest indexed candidates, profile records, trust review, review history, and pagination stay available here.
Updated in 180 daysuse-agently

This is a CLI gateway to Agently's marketplace of AI agents, tools, and APIs. It routes all MCP, HTTP, and A2A protocol calls through a single interface that handles wallet management and x402 micropayments on Base. You search for agents, inspect their capabilities, then call them with built-in cost transparency (dry run first, pay after approval). The docs...

Review links
Updated in 180 dayscrewai-multi-agent

CrewAI gives you multi-agent orchestration without the LangChain baggage. You define agents with roles and goals, chain tasks together, and let them collaborate autonomously on complex workflows. It's built for production use with memory, 50+ built-in tools, and decent observability. The sequential and hierarchical process modes cover most patterns, from si...

Review links
Updated in 180 daysgodot-mcp-setup

This handles the setup and configuration of Godot's Model Context Protocol server so AI agents can programmatically build and modify scenes. It's specifically for when you want automated scene creation rather than manual workflows. The main piece is a tool script that generates the Claude Desktop config JSON you need to get MCP running with Godot. Don't exp...

Review links
Updated in 180 daysiii-agentic-backend

A lightweight framework for building multi-agent systems using queues, shared state, and explicit handoffs between single-purpose agents. If you've used LangGraph or CrewAI, the pattern will feel familiar, but this leans into HTTP triggers and pub/sub for orchestration rather than complex graph structures. The approval gates concept is smart: each agent exp...

Review links
Updated in 180 dayssolana-agent-kit

This is SendAI's open-source toolkit for building AI agents that can autonomously execute Solana blockchain operations. It wraps 60+ actions across tokens, NFTs, DeFi protocols like Jupiter and Raydium, staking, and bridging into a plugin architecture that works with LangChain, Vercel AI SDK, or Claude via MCP. You'd reach for this when you want an AI agent...

Review links
Recent page 406 / 417 · 5000 listings

PreviousNext pageNext page JSON

Stale WatchlistStale candidates, governance queue links, review history, and pagination stay available here.
Stale page 3 / 3 · 27 watchlist items

PreviousOpen governance queue

Review support

Review links

Freshness cards stay readable; re-review records and profile resources stay linked here.

Open Freshness feed JSON
Supporting review linksLinks, review order, and page-specific notes remain available here.
  • Use the structured freshness record instead of raw feed polling when a reviewer needs update context.
  • Use pagination.nextPageUrl to continue through the recent-update index.
  • For latest recommendations, use recentUpdates[] but still fetch profileJson, trustJson, trialJson, and installJson before action.
  • Use staleWatchlist[] to identify candidates that need source freshness evidence, then open /re-review.json for pause, re-test, or retire decisions.
  • Do not treat a fresh source update as safety approval; inspect trustJson, evidenceJson, and installJson first.
Freshness review path
  1. 01Site contextShared review rules
  2. 02Freshness watchOpen the focused review record
  3. 03Profile pageOpen the candidate page
  4. 04Profile resourcesEvidence, setup, trust, trial, and history files

Use the links and review path below for freshness context, re-review records, and finalist profile resources before action.

Review route: OpenAI review tools can start with openai.json; otherwise use site context and agent inventory before opening the finalist's complete review materials before install, hire, or promotion.