Havuz

AGENTS.md contract for AI coding agents + zero-dependency linter + SessionStart hook. Works with Claude Code, Codex, Cursor, Copilot.

Bounded Meta Ads copilot with MCP tools, progressive Skills, context, Memory and safe Draft workflows

System One Coding Agents: code-level answers at the same score as Claude Fable 5.1 on the same 74-point xz benchmark (69 / 74, 93.2 % each),

Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.

文件化经验库：让 AI agent 不再重复踩同一个坑。方法论 + 模板 + 可选工具。

Instant context compaction for Hermes Agent. Builds the compaction summary in milliseconds with no LLM call, keeping the exact commands, exi

Context layer for AI agents in vertical SaaS: domain events in, a bitemporal context graph per end-customer out, five MCP tools for every ag

An open standard for agent-native software requirements.

Pensieve: never lose the thread. A local MCP server and Mac app that links your files, repos, agent sessions, tickets and messages into one

A Claude Code workflow for long projects: short context, decisions remembered, lessons that stick across sessions

AI-KIT is a practical starter kit for development: ChatGPT/Codex, Claude, DeepSeek, KIMI, and other coding agents. It provides reusable proj

Context management proxy for AI coding agents: verbatim archive, on-demand recall, and saved engine state on supported backends.

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive

CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and e

Stop paying the multimodal tax. Your AI agent keeps every image it has seen but only sends the ones it needs: lighter chats, no endless reco

mu, coding agent kararlarının bir kısmını küçük bir judge modeline devrederek pi tabanlı CLI ve desktop agent sunar.

Neden yükseliyor · 14 günlük yaşına rağmen 386 yıldız, son 28 günde 731 commit ve 11 farklı yazar raporlanıyor; bu kısa sürede dikkat ve geliştirme hareketliliğine işaret ediyor. Ancak bu veriler kalıcı benimseme veya üretim olgunluğunu tek başına kanıtlamıyor.

Intent-Router, belirsiz istekleri inceleyip eksik noktaları soran ve yönlendirme öncesinde makinece okunabilir bir IntentSpec üreten bir agent skill’idir.

Neden yükseliyor · Altı günlük bir repoda 141 yıldız ve 81 commit dikkat çekiyor; ancak commit’lerin tek yazardan gelmesi, ilgiyi bağımsız geliştirme veya benimseme kanıtı olarak yorumlamayı sınırlıyor. README’deki ölçümler de küçük örneklemli (N=5 ve N=3) ve proje tarafından raporlanmış.

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt.

Self-hosted evidence store for coding agents.

Local CLI and MCP server for compacting test and build output, with retrieval from a redacted local cache.

Self-hosted AI coding agent platform for GitLab, built with LangGraph. Reviews merge requests, resolves issues autonomously, and chats with

The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into

Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessions, with knowledge graphs, hy

Gobstopper is an intelligent compaction proxy for Claude Code and Codex. It compacts more often, keeps history local, and cut tokens 29% on

Open-source skills for designing and reviewing software with AI agents

Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cu

Your coding agent starts every session knowing nothing about your project. One line, and it writes its own memory from your real code, then

AI remembers, you find. File-based long-term memory and project maps for any AI coding tool, plus a zero-dependency governance CLI for chang

Portable, verifiable work state for coding agents

Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command,

Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in tool

Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.

Dissenyador visual de workflows i graphs d’IA agentiva · Diseñador visual de workflows y graphs de IA agéntica · Visual designer for agentic

The context exoskeleton for AI development: optimize the entire development lifecycle to reduce token usage and context occupancy.

Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex and Pi.

Entente — provenance engineering for coding agents: handoffs become confirmable, verifiable, retryable contracts; agents form a network with

The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing tha

Local-first cross-session long-term memory for DeepSeek Harness — 22 narrow tools, hybrid FTS5 + local-vector retrieval, evidence gate, prov

Reverify, AI agent’larının reverse engineering ve kod doğrulama iddialarını deterministik araçlarla sınayan, CLI ve MCP server sunan bir Python aracıdır.

Neden yükseliyor · Repo yalnızca 28 günlük olmasına rağmen 1.245 yıldıza ve son 28 günde 83 commit’e ulaşmış; AI agent’ları için doğrulanabilir çıktı ihtiyacıyla MCP entegrasyonu dikkat çekmiş olabilir. Dört farklı yazarın katkısı aktiviteyi destekliyor, ancak yıldızlar tek başına benimseme veya kalite kanıtı değil.

Your AI forgets every session. Give it a memory it can trust: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code

A tool that replaces everything that can be deterministic in repository work: search, symbols, callers, task scope, history, review and Git

立正 hakkında kamuya açık içerikleri kaynak bilgileriyle düzenleyip yerel arama ve RAG tabanlı uygulamalar için sunan bir Python deposudur.

Neden yükseliyor · 29 günde 115 yıldız, yeni içeriklerin ve İngilizce kaynakların genişletildiğine işaret ediyor; README ayrıca bu veri tabanını kullanan bir topluluk türevinden söz ediyor. Bunlar erken ilgi göstergeleri, ancak 28 günde 4 commit ve tek yazar, sürdürülebilirlik veya geniş benimseme için henüz sınırlı kanıt.

Local memory for Codex. Reuse work across chats without LLM calls to organize it.

给你的AI订一份晨报：常驻agent的信息摄入与跨context认知循环（思路篇，无代码）

OpenContextEngine is a self-hosted, ACE-compatible code retrieval service. It indexes source files with cAST-aware chunking, stores metadata

Local-first persistent memory for OpenAI Codex: governed recall, progressive disclosure, no hosted vector database.

I'm sad: such a great project, yet no one has starred it.

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

GatherThread 共序：本地 AI 编程 Agent 多人联机协作、实时共享上下文。Self-hostable collaboration for local AI coding agents, Codex Desktop connector & DeepSeek Har

Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model,