|
Optimize Your Agent — Save Tokens, Cost, and Time
Optimize the agent workflows you run again and again. Copy one prompt into Codex, Claude Code, or another agent and measure the savings in tokens, cost, and...
|
83 % |
|
AgenticMeter — Observability for AI Agents
|
81 % |
|
Agentree | Supervise Multiple Coding Agents in One Graph
Supervise multiple coding agents in one graph. Branch from any agent message, run isolated worktrees, and write plain-English workflows for multi-step coding...
|
81 % |
|
Wont · Your agents shouldn’t solve the same problem twice
Wont finds the work your AI agents keep repeating and turns it into a verified, instant path. When it isn’t sure, it hands the task back to your agent.
|
81 % |
|
Agent Basin — Observability & Replay for AI Agents
Every agent run. Captured, searchable, replayable. Agent Basin is the missing flight recorder for AI agents in production — capture every tool call, decision...
|
80 % |
|
topyourproduct — agents that put your product in the answer
A team of AI agents reads your site, finds why engines aren't mentioning you, and ships the fixes. Every step of the reasoning is visible.
|
80 % |
|
GenSwarms: the operating system for AI workforces
GenSwarms runs AI agents as separate, supervised processes on declared message paths, with an API and a live event stream. Open source, MIT.
|
80 % |
|
Deslopus — Make Coding Agents Produce Less Slop
Deslopus is an open-source initiative to make AI coding agents write code that survives the next change.
|
80 % |
|
Machineble — Agent-readiness audits for e-commerce
Machineble sends real AI agents to your store, scores schema.org, llms.txt, MCP, UCP, ACP and robots.txt, and returns an agent-readiness score with a fix lis...
|
80 % |
|
STMA — AgentOps for coding agents
STMA is AgentOps for teams that build with coding agents: a live map of every agent run, collision warnings before two agents touch the same ground, team rul...
|
80 % |
|
Pushyou — Your agents work. You decide.
The phone inbox for your AI agents and automations. Claude Code, Codex, scripts and n8n report their results and ask when a decision is yours. Answer in a ta...
|
80 % |
|
Covector · ctx-loop — living context for AI coding agents
Give your agent context that stays true. ctx-loop gives you — and your team — living context: small, sourced, expiring cards your agent pulls in fresh, every...
|
79 % |
|
iofold - Automatic Evals for Autonomous Agents
Add iofold's evals ↔ optimization loop in 10 minutes. Code + LLM-as-judge evals, written by a deepagent with data science tools and backtesting. Meta-prompti...
|
79 % |
|
CREAO AI │ Agents that run your business
CREAO builds AI agents that run your work. They plug into your existing tools, learn how you operate, and compound your knowledge around the clock.
|
79 % |
|
Visceral
Visceral is the optimization layer for AI agents. We mine your traces, find the waste, and prove every fix on your own traffic before it ships: no hardware c...
|
79 % |
|
OakAuth - AI Agent Permission & Observability
Control what your AI agents can do. Monitor every action. Know not just what happened, but why.
|
79 % |
|
swiz — hooks for AI coding agents
|
79 % |
|
Agent Reading Test
A benchmark that tests how well AI coding agents can read web content. 10 tests, 20 points.
|
79 % |
|
Code for Agents · Make your codebase a place agents can work
AI coding agents fail in codebases built only for humans. Learn what agent-legible code looks like and how to get there.
|
79 % |
|
AgentRank. The benchmark for developer-tool adoption by coding agents.
AgentRank runs Claude Code and Codex in real, controlled repositories and records whether your tool gets named, installed, compiled, and kept. Then we diagno...
|
79 % |
Detected social media networks