Showing:
tag “ai-agents”
Reset
JavaScript
Stable
May 15, 2026
Tavily's MCP server gives AI agents like Claude real-time web search, extraction, crawling, and site mapping through a single integration. It's one of the more polished MCP servers out there, but it comes with the usual tradeoffs of depending on a paid third-party API.
1,698 stars
tavily-ai/tavily-mcp
7 min read
TypeScript
Peaking
May 11, 2026
GSD 2 is a standalone TypeScript CLI that wraps LLM coding agents with real session management, spec-driven execution, and autonomous milestone progression. It's genuinely ambitious, actively developed, and rough enough around the edges that you should know what you're signing up for.
5,380 stars
gsd-build/gsd-2
7 min read
Rust
Stable
May 6, 2026
Vibe Kanban hit 25k stars by solving a real problem: managing multiple AI coding agents across a project without losing your mind. The catch? The company behind it, Bloop, is shutting down — and that changes everything about whether you should adopt it.
25,141 stars
BloopAI/vibe-kanban
8 min read
TypeScript
Peaking
May 5, 2026
RuFlo (formerly claude-flow) has 31k stars and a release cadence that would exhaust most teams. But between the impressive architecture diagrams and the 448 open issues, there's a real question worth answering: is this production-ready or just a very polished demo?
31,234 stars
ruvnet/ruflo
8 min read
Python
Breakout
May 2, 2026
NousResearch's Hermes Agent just crossed 126k stars with nearly 14k gained in a single week. I dug into what it actually does, where it delivers, and where the 7,300 open issues should give you pause.
126,480 stars
NousResearch/hermes-agent
8 min read
TypeScript
Peaking
May 1, 2026
RuFlo (formerly claude-flow) is a multi-agent orchestration framework built around Claude Code that's been trending hard. I dug into the repo to figure out whether the star count reflects real utility or just good marketing.
31,234 stars
ruvnet/ruflo
7 min read
Stable
April 26, 2026
The claude-codex skill lets you delegate prompts from Claude Code to your local Codex CLI — second opinions, code review, implementation runs — without touching credentials. It's a narrow, well-scoped bridge between two AI coding tools, and it mostly does what it says.
111 stars
claude-codex
6 min read
Python
Rising
April 23, 2026
The Agentic Context Engine (ACE) adds a persistent learning loop to AI agents so they stop repeating the same mistakes across sessions. It's early-stage but backed by real benchmarks, active development, and a surprisingly clean API.
2,131 stars
kayba-ai/agentic-context-engine
7 min read
Python
Rising
April 22, 2026
The Agentic Context Engine (ACE) promises to make LLM agents learn from their mistakes across sessions using a persistent 'Skillbook' — no fine-tuning, no vector databases. It's early-stage but the architecture is genuinely interesting and the benchmarks are hard to ignore.
2,131 stars
kayba-ai/agentic-context-engine
8 min read
Python
Rising
April 12, 2026
DocsGPT is a self-hostable, open-source RAG and agent platform with 17k+ stars and active weekly commits. I dug into whether it's actually production-ready or just a well-marketed demo.
17,818 stars
arc53/DocsGPT
8 min read