Code agents

transformers safetensors gemma4_unified_assistant text-generation gemma4 gemma4-assistant

transformers safetensors sdar text-generation conversational custom_code

transformers gguf mistral quantized 2-bit 3-bit

transformers gguf llama text-generation GGUF conversational

Model Optimizer safetensors kimi_k25 ModelOpt Kimi-K2.7-Code quantized

transformers safetensors gguf qwen2 text-generation qwen2.5-coder

gguf text-generation base_model:01-ai/Yi-Coder-1.5B base_model:quantized:01-ai/Yi-Coder-1.5B license:apache-2.0 endpoints_compatible

gguf distillation qwen2.5 qwen2.5-coder code adi

mlx safetensors kimi_k25 kimi kimi-k2 moe

gguf code qwen qwen-coder codeqwen text-generation

transformers safetensors qwen2 text-generation text-to-sql sql

transformers safetensors qwen2 text-generation code codeqwen

transformers safetensors qwen3_5 image-text-to-text text-generation-inference unsloth

transformers gguf code codeqwen chat qwen

gguf unsloth text-generation en license:apache-2.0 endpoints_compatible

mlx safetensors qwen3_5 mlx-lm apple-silicon fable5

transformers safetensors phi4mm text-generation nlp code

nemo safetensors nemotron_h text-generation text-generation-inference transformers

gguf gemma4 coding agentic terminal tool-use

transformers safetensors gguf agentic coding tool-use

gguf gemma4 coding agentic terminal tool-use

mlx safetensors gemma4_assistant mlx-vlm gemma-4 gemma-4-26b-a4b

gguf llama.cpp speculative-decoding mtp gemma4-assistant draft-model

transformers safetensors gemma4_unified_assistant text-generation compressed-tensors marlin

gguf quantized GGUF quantization imat imatrix

mlx safetensors qwen2 code codeqwen chat

mlx safetensors qwen2 text-generation conversational base_model:Qwen/Qwen2.5-Coder-3B-Instruct

llama.cpp gguf quantized distillation sft reasoning

A coding agent in 5 files, plus a skeptic that catches it faking the fix — verify AI code with a check the agent never saw. Runs on any model (OpenRouter/OpenAI/Ollama).

欲しい機能を言うと、アプリが自分で作る。ただし暴走はしない。安全な自己進化型デスクトップAIエージェント / Self-evolving desktop AI agent with safety gates

Autonomous Terraform agent takes a prompt or Jira ticket, runs a full validation pipeline, and opens a GitHub PR. No human in the loop.

fabius v2.3.1 — the autonomous AI agent that runs on every major model. Fifteen sealed skills, one stance: scout wide, strike narrow. A 22-rule proven decision core + researched frontier layer, the IDENTITY contract, and the 100-task FBS benchmark (BASE→FAB→FAB_MEMORY). Whitepaper, 50pp.

transformers gguf agents agents-a1 kimi coding

gguf agents agents-a1 kimi coding sft

transformers safetensors sdar_moe text-generation conversational custom_code

gguf text-generation arxiv:2401.06066 base_model:deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct base_model:quantized:deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct li

transformers gguf code agent agentic-coding moe

gguf text-generation license:apache-2.0 endpoints_compatible region:us conversational

Multi-agent deep research for Claude Code. Zero API keys. Paste one line, type /research.

A DevOps/SRE runbook agent: it ingests Prometheus Alertmanager alerts, triages them with an LLM against a closed set of pre-approved runbooks, and executes remediation steps through a safety chain of input validation, human approval, and automatic rollback.

Run an AgentScope 2.0 agent workbench in minutes — no model key required. Native AG-UI + assistant-ui scaffold with SSE streaming, tool calls, and write-tool confirmation.

Autonomous agent on ESP32-S3 that rewrites its own Python source at runtime.

A job-application app whose backend is a headless LLM agent (Claude Code CLI). Markdown + git as the database.

端到端中文法律咨询 Agent：自研轻量调度框架、法条 RAG 与公网案例双源检索、NDJSON 流式 Web UI、自修复链路与运行指标观测

Easy-to-use, customizable, high-quality threat modeling skills for AI agents.

Deep-research LLM agent + RAG platform for internal bank-product audit — cited reports, PDF export, pgvector

LangGraph CLI agent that analyzes a GitHub repo and produces a tech due-diligence report

Claude Code skill that ships a full production feature while you sleep. No push, you review.

AI-powered OSINT & security reconnaissance toolkit for Python — subdomain finder, WAF detector, JWT analyzer, email breach & SPF/DMARC checker, GitHub secret scanner + a natural-language LLM agent. For bug bounty & pentesting.

Small Python Agent runtime with planning, memory, tools, state machine, and multi-agent review.

Template file system mcp server

A persistent cognitive entity — one agent, one memory, one timeline across all platforms. Self-editing knowledge graph, cross-platform identity, P2P network.

Async FastAPI LLM agent with LangGraph routing, scope-aware tools, deterministic verification, bounded recovery, evals, and durable traces.

Satellite-native crop yield intelligence: Spatio-Temporal Transformer + live Sentinel-2/ERA5 via Google Earth Engine, FastAPI backend, and an LLM tool-calling agent (Groq/Llama 3.3) with guardrails and automated eval. Research prototype — synthetic training data, documented known issues.

一个 7×24 小时不间断运行，帮你跑实验、用 Git 维护公开仓库、更新 LaTeX（Overleaf）论文的科研自动化工作流。实测效率提升 25 倍。Claude Code Skill，一条命令装进任意项目。

A 股多智能体投研编排系统：7 个专职 subagent 以文件契约协作，长文档上下文隔离，数字 claim 双源核验，公司与行业双研究链路

A threat hunter that lives in your terminal with memories in Notion.

An AI-powered EEG classifier that detects emotional states during music listening and curates Spotify playlists grounded in what your brain actually did.

Claude Code / Codex skill for authoring and reviewing SuperDialog voice-agent playbook YAMLs — schema reference, 15-point failure-pattern checklist, interrupt-guard code pattern

Zero-dependency LLM agent runtime — tool use, MCP, sandboxed self-written tools, checkpoint/resume, approval gates, bi-temporal fact memory, code-level guards (context bounds, loop guard, egress control, shadow mode), declarative tool policy, OpenTelemetry. Not a framework. 885 tests, CI Linux/Windows, 31 runnable demos, online visual builder.

企业级 RAG 知识库问答系统 + AIOps 运维诊断 Agent(Plan-Execute-Replan / LangGraph / MCP)

Deterministic, inspectable workflows for coding agents. Kilin is a local, CLI-first workflow runtime: describe a workflow in plain files, validate it before anything runs, then execute it through Codex, Claude Code, or OpenCode with explicit approvals and persisted runs.

LibreControl — one universal /remote-control for every coding agent you run (Claude Code, Codex, Gemini, Cursor, Copilot, any MCP tool), across all your machines, centralized into the single chat app you choose: Telegram, WhatsApp, Slack, Signal, Discord. Self-hosted, with approvals and audit.

Engineering discipline for AI harnesses. Drop-in skill library for LLM coding agents.

Self-hosted, governed-autonomy SRE platform: an LLM agent that autonomously remediates infrastructure incidents behind a fail-closed prediction gate, mechanical verdicts, and a tamper-evident ledger. The agent can't act on a belief it hasn't checked.

Best AI Code Architect 2026: Diagram-First Agent Orchestrator with AST Editing & Atomic Commits

Give your AI agent a phone — a thin Python CLI over the BlueBubbles REST API to read, search, send, react, and attach in iMessage, with draft-then-confirm send gating and an agent-facing SKILL.md.

Benchmark code and interactive results for autonomous network-attack detection by tool-using LLM agents investigating raw PCAPs.

AI agents built spaCy model recommenders, then a fresh AI peer-review panel rejected all three

Post-response grounding check + cross-family adversarial review for LLM chat agents

Локальный модуль машинного зрения для LLM-агентов на чистом Rust: метрический 3D scene-graph каждый кадр, MCP-сервер, $0/CPU/приватно

Agent-ready project documentation template with START/STATE/TODO/DONE, workflows, lightweight tooling, and LLM-friendly project memory. Independent project - not affiliated with Anthropic, OpenAI or Google.

Benchmarked Claude Code plugin that makes cheaper Claude models (Haiku, Sonnet, Opus) match Fable 5's output at a fraction of the token cost — auto-routed reasoning levels, verification discipline, closed-loop habit correction, statusline HUD with usage meters, and a portable AGENTS.md export for any AI coding agent.

Research-first, brand-agnostic blog drafting engine for Claude Code — keyword research with SERP-ownership choice, an enforced adversarial editor, validated citations, and CMS-ready output.

Claude Code Workflow that executes cys:plan implementation plans with independent tasks running in parallel via a dependency DAG — ships the cys plugin (design, plan, run, check, ship).

An AI agent that falls deeper into any topic — books, papers, podcasts, and videos, all connected.

Runtime-neutral protocol for growing adaptive marketing agents: role + playbook + GEB learning, with schema validators and CI gates enforcing it. Pure spec — bring your own runtime (Codex, Claude Code, MCP, etc.).

LEASH-8: an 8-domain control model for AI agents with delegated authority. Scorecard, approval-design checklist, plan-vs-authorize pattern. Patterns from a live production agent operation, sanitized. Free, MIT.

Pediatric dose-extrapolation agent: a defensible starting dose for a child from adult pharmacokinetics via allometry × organ maturation, with a cited, graded, auditable rationale. Multi-agent (Opus + Sonnet, live PubMed/openFDA). Decision support, not prescribing.

Local AI Linux troubleshooting agent with llama.cpp, safe command execution, system diagnostics, Docker support, CLI, and web GUI.

163 specialist Claude Code agents + 24 routing skills + 16 strategy playbooks. Korean/Japanese Business Navigators, game-dev (Unity/Unreal/Godot/Roblox/Blender), XR/spatial, paid-media routing. skill-routing-arbitrator disambiguates the ~500-skill ecosystem. Fork of msitarzewski/agency-agents.

Evidence router & policy engine for coding agents — enforces source choice and proof-of-use through Claude Code hooks, including routes to MCP tools. Local-first; no LLM in the hook loop.

TeleAgent AI is an enterprise-grade, agentic omnichannel consumer intelligence engine engineered specifically for Deutsche Telekom AG (Germany & Europe) under Problem Statement 5: Omnichannel Consumer AI Engine for Digital Commerce.

GSD lifecycle orchestration as a native OpenClaw plugin — enforced research→plan→execute→verify→ship, hybrid retrieval, 0 Discord slots

Multi-agent collaboration engine with persistent, searchable, self-compacting memory. Agents research, critique and adjudicate over a shared SQLite memory with hybrid BM25 + embedding recall. Zero-dependency core, runs locally on Ollama.

Survivability-first quantitative research system. An AI council debates every architecture decision before code; deterministic, tested strategies do the trading. Walk-forward + purged CV + deflated Sharpe. LLMs never place trades.

Local-first Python toolkit for parallel Claude and LLM agent orchestration: consensus voting, stigmergy, boss-worker swarms, and benchmarks

AI-SOC — detects, explains and contains cyberattacks on critical infrastructure. Isolation Forest detection + RAG/MITRE attribution + policy-gated response, wired end-to-end. ET AI Hackathon 2026, PS7.

Let AI coding agents (Claude, Codex, Pi) see and control your Bevy game - remote input injection, screenshots, and frame-synced feedback over a simple JSON-lines TCP protocol.

Rich Brain / Clean Hands: a two-brain delegation pattern for LLM agents that keeps the deciding brain's context clean and exiles heavy work to an isolated executor.

More human oversight can make an AI agent less safe. Headroom is a human-in-the-loop firewall for coding agents that measures when to trust the human: oversight as resource allocation, not just classification.

An agentic buyer's agent for an unrepresented Bay Area home purchase — deterministic Python core, LLM at the edges.

MCP server for Cognigy.AI - 132 tools that let Claude, Cursor & other AI assistants build, configure, test & operate conversational AI agents via the Model Context Protocol.

Security & runtime checklist for moving LLM agents from demo to production: HITL gates, idempotency, prompt injection boundaries, tool risk classification (CC BY 4.0).

Decision governance for code and the agents editing it — track PRD→ADR→SPEC decisions, map them to files, and gate changes against them. Deterministic, honest CLI + MCP.

Deterministic execution harness for AI agents — goals in, structured tasks out, verified results back.

Infer least-privilege MCP tool policies from agent traces

Graph RAG on SQLite for AI agents: vector retrieval + hand-curated wikilink graph + cross-encoder rerank, with a zero-token per-turn memory ledger. Working pilot.

ETH Zurich thesis project: a nine-agent AI pipeline for quant research, from hypothesis to backtest report

Judgment continuity for AI agents — load your project's scars, taste, and non-negotiables into every session. Judgment-layer companion to edda. (formerly project-doctrine)