Havuz

HarnessRouter, farklı agent harness’lerini oturum, streaming ve dosya desteğiyle tek bir API üzerinden kullanmaya yarayan self-hosted bir altyapıdır.

Neden yükseliyor · Agent harness’lerini tek arayüzden kullanma vaadi güncel bir altyapı ihtiyacına hitap ediyor. 49 günlük repo için 2.675 yıldız ve son 28 günde 271 commit ile 10 farklı yazar, belirgin ilgi ve kayda değer geliştirme hareketi gösteriyor; ancak bu metrikler benimsemenin veya üretim kalitesinin kanıtı değil.

Paritok, coding agent isteklerini LLM'e iletmeden önce sıkıştıran ve sıkıştırılmış içeriğin gerektiğinde geri alınmasını sağlayan bir gateway'dir.

Neden yükseliyor · Token maliyeti ve context window kullanımı coding agent ekipleri için görünür sorunlar; drop-in entegrasyon vaadi anlaşılır bir değer önerisi sunuyor. 74 günlük repo için 1.453 yıldız ve son 28 günde 12 commit, 4 farklı yazar ilgi ve yakın dönem aktivitesine işaret ediyor; bunlar tek başına ürün kalitesini kanıtlamıyor.

SandBase Harness, AI agent'ları yerel veya self-hosted ortamda çalıştırmak ve oturum, araç erişimi, bellek ile denetim süreçlerini yönetmek için bir runtime sunuyor.

Neden yükseliyor · 78 günlük yaşına göre 674 yıldız ve son 28 günde 1012 commit dikkat çekiyor; ancak commit'lerin tek yazardan gelmesi bağımsız ilgi ve sürdürülebilirlik kanıtını sınırlıyor. Eldeki ölçümler yıldızların ne hızla arttığını göstermiyor.

dshcloud, DeepSeek Harness için kullanıcı başına izole ve kalıcı çalışma alanları sunan, self-hosted çok kullanıcılı bir platformdur.

Neden yükseliyor · 18 günde 87 yıldız ve son 28 günde 106 commit dikkat çekiyor; ancak commitlerin tek yazardan gelmesi, bu hareketliliğin geniş katkıcı desteği veya olgun benimseme anlamına gelmediğini gösteriyor.

PGX — Lightweight Postgres for AI agents. Written in Rust. Thousands of isolated databases in one runtime🐘

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies

TypeScript execution journal for retryable tools: SQLite durability, lease fencing, explicit uncertainty, and reproducible crash tests.

Autumn-Recruit Algo Notes(秋招算法学习仓库)，面向大模型时代的算法、工程与AI学习共建仓库。从数学基础、数据结构，到机器学习、深度学习、LLM、Agent、AI-Infra、语音与数据科学，通过「理解→推导→手写 → 运行 → 验证 → 复盘构建可持续迭

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can ex

Open-source Rust TemporalStore for LLM context management, temporal features, and risk control

the agi compiler: records llm agent behavior, proves what repeats, and compiles it into verified, sandboxed wasm binaries that run for micro

Intelligent multi-LLM router with task-aware routing strategies, cost optimization, and production safety controls — drop-in OpenAI-compatib

Deterministic memory layer for your agents

SDK, skills, and examples for Inkbox: give AI agents a persistent identity with email, phone number, and internet address

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

Open-source AI agent runtime built in Rust. Define once, deploy isolated instances per tenant with built-in memory, encrypted vault, self-ex

半人马环 Centaur Loop：AI 员工的最小工作单元框架。把复杂岗位拆解为可由 AI 接管、由人类治理、由反馈和记忆持续进化的循环工作流 / The smallest work unit for building AI employees.

The living armor an AI agent inhabits: eternal devouring, eternal evolution, eternal amplification.

Lightweight Linux sandbox for AI agents. Kernel-native isolation (namespaces, cgroups, seccomp, Landlock) with REST API, MCP bridge, and web

Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely release self-hosted models behind

Explore data center power continuity, energy ledgers & infrastructure assumptions through reproducible synthetic models.

Stateless LLM runtime that dynamically routes, loads, executes, and unloads models per request with bounded VRAM caching and intelligent mod

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out

croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and en

Runtime economic governance for AI agents. Circuit Breaker adds risk-managed execution, cost ceilings, and kill switches to autonomous AI wo

Simple deployment tool to deploy your Hermes Agent to Cloud

High-throughput, self-hostable LLM router in Go. BYO provider keys, k8s-native, key pooling + batch + usage observability.

Run coding agents autonomously with isolated Git worktrees, independent verification, and human-controlled integration.

Distributed, peer-to-peer, decentralized network for LLM inference — peers seed & leech completions, metered by BitTorrent-protocol-style up

Pause your AI agent. Ask a human. Resume with their answer. Open source human-in-the-loop (HITL) library for production LLM agents: Slack, e

🚀 One API gateway for GPT, Claude, Gemini, DeepSeek and more. OpenAI-compatible API for developers.

AI 漫剧/短剧连载创作引擎（Agent Skill）| 一句话到剧本+分镜+配音+AI提示词的工业化流水线 | 七个记忆文件+22项跨文件一致性检查，解决长线连载人设崩坏与伏笔丢失 | Agent-agnostic (Claude Code / Codex / Copilot

Semantic cache strategy bench: replay recorded request traces through candidate caching policies and measure which one actually pays off.

Declarative Python SDK for building AI inference platforms on Kubernetes — bare machines to a served model, composed rather than hand-assemb

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

Open-source, self-hostable server and runtime core for Run402 — backend infrastructure for AI agents. Postgres/PostgREST with RLS, storage,

Hands-on GPU/HPC infrastructure operations: K8s GPU scheduling, HAMi sharing, Slurm, observability & vLLM inference. Learn it free on a lapt

Turn failed AI agent runs into replayable regression tests. Catch regressions before you ship.

Per-key smart routing for New API: automatic failover, shared health, self-healing recovery, actual-route billing, and explainable decisions

Recall what · where · when. Sync your AI coding agents across machines: git config-sync + a peer-to-peer transcript relay to your own NAS (o

Open-source local AI server configs, GFX906 runtime maintenance, reproducible benchmarks, and QC methods for affordable AI research infrastr

AI Infra 推理系统学习资料：从深度学习算子到 vLLM 服务端部署

Generate and maintain AI-readable project memory, worklogs, and handoffs for any repository.

High-precision quota and token monitoring for AI Agents. Real-time analytics and usage tracking for Claude, Codex, Gemini, and Copilot to pr

Self-hosted Rust LLM API gateway with OpenAI-compatible and Anthropic-compatible APIs, model routing, multi-tenant keys, usage tracking, bil

Research and shared data contracts for Pick Your AI: component catalogs, compatibility rules, pricing, and evidence for AI stacks.

A production-oriented LLM engineering platform with OpenAI-compatible serving, streaming, observability, evaluation, reproducible experiment

Evidence-backed structural validation of Kimi K3 UD-IQ1_M and UD-Q4_K_XL split GGUF releases using OMIV.