理解、编写、审查或执行代码的 Agent 与工具。
规则推断分类 · 同一项目可属于多个分类
主榜项目至少要有两个当前有效的评分维度,且覆盖两种数据源。综合分 = 可观测采用度(45%)+动量(30%)+关注度(25%);过期或缺失信号不计分。
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
153.0k 可观测/月 115.1k ★ ▲ 6.1k ★/周 3/3 当前信号
Autonomous coding agent as an SDK, IDE extension, or CLI assistant.
424.8k 可观测/月 71.5k ★ ▲ 220 ★/周 3/3 当前信号
Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry.
288.8k 可观测/月 33.7k ★ ▲ 597 ★/周 3/3 当前信号
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
301.9k 可观测/月 32.7k ★ ▲ 115 ★/周 3/3 当前信号
Open source device layer for AI coding agents: a CLI, MCP server, and typed Node.js API to control mobile, web, TV, and desktop apps on devices and simulators, locally or in the cloud.
2.9M 可观测/月 5.3k ★ ▲ 86 ★/周 3/3 当前信号
MCP server to provide Figma layout information to AI coding agents like Cursor
674.1k 可观测/月 16.2k ★ ▲ 46 ★/周 3/3 当前信号
Token-efficient MCP adapter for Pi coding agent
1.9M 可观测/月 1.6k ★ ▲ 9 ★/周 3/3 当前信号
Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client. Free for non-commercial use; commercial use needs a one-time license.
29.4k 可观测/月 2.8k ★ ▲ 8 ★/周 3/3 当前信号