Official implementation of The Trinity: Capability-Driven Recursive Self-Improvement for Multimodal Agents.
GitHub repository with 47 stars and 4 forks.
Language: JavaScript
Topics: ai-agents, capability-learning, harness, multimodal-agents, real2sim2real, recursive-self-improvement
Trending score 0.96, freshness score 0.50, stars gained +6, forks gained +0.
2026-11-03: 47 stars and 4 forks.
在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap.
GitHub repository with 57,612 stars and 1,566 forks.
Trending score: 6.43; stars gained: +2,952; forks gained: +71.
Language: JavaScript
Topics: ai-agents, deepseek, deepseek-harness, developer-tools, dsh, dsh-plugin
DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分
GitHub repository with 16,365 stars and 3,766 forks.
Trending score: 6.30; stars gained: +1,650; forks gained: +355.
Language: JavaScript
Topics: deepseek, deepseek-harness, dsh-plugin, dsh-plugins, harness-jailbreak, jailbreak
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
GitHub repository with 57,518 stars and 3,740 forks.
Trending score: 6.24; stars gained: +2,101; forks gained: +127.
Language: JavaScript
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
GitHub repository with 295,759 stars and 43,757 forks.
Trending score: 6.16; stars gained: +1,588; forks gained: +217.
Language: JavaScript
Topics: ai-agents, anthropic, claude, claude-code, developer-tools, llm
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
GitHub repository with 108,871 stars and 7,326 forks.
Trending score: 6.03; stars gained: +1,661; forks gained: +77.
Language: JavaScript
Topics: agent-skills, ai-agents, anti-slop, claude-code, codex, cursor
Orkas is an open-source (MIT), local-first AI team for your desktop: a Commander turns your goal into to-dos and coordinates 16 built-in specialist agents plus Claude Code, Codex, OpenCode, OpenClaw and Hermes, with projects, scheduled automations and connectors. Free app for macOS & Windows; built-in models or your own keys.
GitHub repository with 7,897 stars and 498 forks.
Trending score: 6.00; stars gained: +1,610; forks gained: +115.
Language: JavaScript
Topics: agent-collaboration, agent-harness, agent-orchestration, agent-team, agent-workflow, ai-assistant
Give AI coding agents the context they need to ship production-quality software.
GitHub repository with 243 stars and 19 forks.
Trending score: 0.00; stars gained: +0; forks gained: +0.
Language: Rust
Topics: ai, ai-agent, ai-agents, ai-assistant, ai-infra, ai-infrastructure
Nipmod package intelligence, Codex plugin, MCP workflows and public agent safety tooling.
GitHub repository with 0 stars and 0 forks.
Trending score: 0.00.
Language: TypeScript
Topics: ai-agents, cli, codex, codex-plugin, developer-tools, mcp
Local knowledge graph for AI agents. Hybrid search + MCP server for Obsidian vaults.
GitHub repository with 171 stars and 16 forks.
Trending score: 0.00; stars gained: +0; forks gained: +0.
Language: Rust
Topics: ai-agents, knowledge-graph, local-first, mcp, obsidian, rag
Source repo for the blog post Stop Stuffing Your System Prompt: Build Scalable Agent Skills in LangGraph
GitHub repository with 14 stars and 1 forks.
Trending score: 0.00.
Language: Python
Topics: agent-skills, ai-agents, ai-systems, claude-code-skills, langchain, langgraph