ShipIt’s Post

🚀 Shipping ShipIt Agent v1.0.5 This release takes ShipIt from a single-agent toolkit to a full multi-agent platform — with prebuilt personas, orchestration, notifications, and cost control baked in. What's new: 🧠 40 Prebuilt Agents across 8 categories Architecture, Code Quality, Security, DevOps, Testing, Planning, Research, and Content. Load in one line with AgentRegistry.default(), search, compose, or override with your own .shipit/agents/ JSON files. 🛠 ShipCrew — Multi-Agent Orchestration DAG-based crews with task dependencies, three execution modes (sequential, parallel, hierarchical), template variable resolution, streaming events, and cycle detection via Kahn's algorithm. 🔔 Notification Hub Slack (Block Kit), Discord (rich embeds), and Telegram (MarkdownV2 with auto-escaping) — all with zero external dependencies. Multi-channel dispatch with severity and event filtering, plus auto-hooks into the agent lifecycle. 💰 Cost Tracking & Budgets Real-time per-call cost tracking across 20+ models, hard budget enforcement with BudgetExceededError, alert callbacks, and model aliases ("opus", "sonnet", "haiku"). 📚 By the numbers → 29 new source files → 4 new notebooks (108 cells) → 4 new doc pages More coming soon. Docs: https://docs.shipiit.com/ GitHub: https://lnkd.in/dpUiYqzF #AI #Agents #OpenSource #DeveloperTools #LLM

We had an interesting engineering problem building Migratowl. When you upgrade 20 dependencies at once and the test suite fails, you have an attribution problem. Which package caused the failure? You could test each package in isolation. Accurate, but that's 20 separate sandbox runs, each taking minutes. Or you could trust the bulk output and guess. Fast — but one failure can look like it's caused by the wrong package entirely. We landed on a hybrid: 1. Run everything upgraded at once first. If tests pass → every package is safe, confidence 1.0. Done. 2. If tests fail, score confidence per package: - Does the error message name this package directly? → high confidence - ImportError or AttributeError for a known API? → high confidence - Major version jump (e.g. 2.x → 3.x)? → confidence boost - Generic failure? → low confidence 3. High confidence (≥ 0.7): fetch changelog, generate report immediately. Low confidence: spawn an isolated AI subagent that tests only that package. The common case (most upgrades pass, or one obvious culprit fails) stays fast. The hard case (ambiguous multi-package failures) gets accurate attribution. The subagent delegation is the part I'm proudest of. Recursive LangGraph agents, each running inside their own K8s pod workspace, merging results back into a single structured report. Repo: https://lnkd.in/dWwZd5Aq Curious if anyone else has tackled multi-agent confidence scoring differently. #kubernetes #python #ai #devops

As a developer, I got tired of the standard code review loop: write code -> push -> wait for a cloud bot (like CodeRabbit) to run -> context switch back to fix the issues -> repeat. I wanted an enterprise grade AI auditor that worked on my *local staged files* before I even committed. Pika Review shifts the audit process entirely to your terminal. It concurrently analyzes your git diffs and generates rich Markdown reports right in your IDE (.pika-reports/). Here is exactly how it helps our daily workflow: - **Shift Left Security:** Flags SQL Injection, RCE, and Path Traversal flaws in your terminal—long before you hit "Push." - **Performance Audits:** Detects mathcal{O}(N^2) bottlenecks and N+1 query patterns before they hit production. - **Multi-Language Support:** A polyglot engine that understands idiomatic risks in TS, Python, Go, Rust, and more. - **Local Markdown Reports:** Generates structured, syntax-highlighted reports directly in your project root. - **Always Free (BYOK):** Unlike expensive SaaS tools, Pika Review is Bring-Your-Own-Key. You can try it out now: https://lnkd.in/gnW3Fp3w I’ve made the tool completely open source and I’m actively looking for contributions and feedback. ⭐ If you find the project useful, please consider dropping a star on the GitHub repo to support its development: https://lnkd.in/gTp_httf Feel free to raise an issue if you spot a bug or want to suggest a feature. Let me know what you think in the comments! 👇 #OpenSource #CodeReview #AI #SoftwareEngineering #DeveloperTools #CLI #GitWorkflow #Programming #CodingBestPractices #pikareview

Curious about daily growing opportunities what #AI can practically do... Checking all new arrivals then I naturally digested the best from every hyped #ClaudeCode skills, hammered it on real projects, and turned it into a workbench I rely on every day... What started as a private dotfiles tweak became a pillar of my daily #OpenSource workflow. Out of the box, agents are role descriptions in a prompt. Mine carry years of OSS maintainer judgment and real SW dev practice, embedded as rules they actually enforce and skills they run by — and I keep refining them as we go. Under the hood: a blend of Anthropic #Claude and OpenAI #Codex — Claude for coding and long-horizon work, Codex as a second-opinion reviewer before anything ships and hand-off coder. Cross-vendor peer review turns out to be a surprisingly strong quality signal, and it buys real #autonomy — I brief once and get finished work, instead of babysitting through several rounds of "did you cover X?" 🤖 Meet AI-Rig — five composable plugins: 🏭 #foundry — 8 calibrated specialist agents (engineer, QA, perf, architect, docs, lint, web, mentor) plus a self-distillation loop so corrections actually stick 🌱 #oss — maintainer survival kit: triage, 6-lens parallel PR review with a Codex pre-pass, feedback resolution, SemVer-correct releases 🛠️ #develop — validate-first discipline: no feature without a demo test, no fix without a failing regression test, no refactor without characterization coverage 🔬 #research — structured ML loop: literature → spec → methodology judge → automated runs with auto-rollback on regression 🗂️ #codemap — one-shot structural index for Python projects; a lightweight CLI (not yet another heavy MCP) that saves a pile of tokens and lets agents finish tasks that used to choke on large codebases The thread tying them together: each plugin is a gate, not a generator. Annoying at first, then quietly indispensable. Give it a spin and let me know what you think 👉 https://lnkd.in/dQSttJ9E #AIEngineering #PythonDev #DeveloperTools #Agents #MLOps #python #caveman #RTK #AgenticAI

What makes lsdefine/GenericAgent interesting is how directly it improves LLM and agent workflows. By tackling the challenge of making agent behavior more reliable, not just more powerful, this project is addressing a key pain point for developers working with LLMs and agents. At its core, GenericAgent is a self-evolving agent that grows in capabilities with each use, forming a personal skill tree. This approach is in stark contrast to traditional methods that rely on pre-trained models and language tags, making it difficult to steer and reuse these tools in real projects. Here are some key highlights of GenericAgent: - Self-Evolving: Automatically crystallizes each task into an skill, allowing capabilities to grow with every use. - Minimal Architecture: 3K lines of core code, with an Agent Loop of just 100 lines, and no complex dependencies or deployment overhead. - Clearly positioned around agentic workflows, making it easy to integrate into existing projects. - Built with Python, making it accessible to a wide range of developers. The traction makes sense: a repository sitting at #5 with around 3,512 new stars in the current trending window is usually solving a problem people can feel immediately. With its strong execution, high compatibility, and token efficiency, GenericAgent is a game-changer for developers working with LLMs and agents. Repo: https://lnkd.in/gwqFex5k #GitHub #OpenSource #GitHubTrending #LinkedInForDevelopers #Python #GenericAgent #AiAgent #Automation

I just shipped a project I'm genuinely proud of 🙂 RepoBrain — a tool that helps AI understand your codebase smarter, instead of dumping the entire source code into context every single query. The results? ✅ 20–40% reduction in token consumption ✅ Meaningful cost savings on AI API bills every month ✅ No more "context window overflow" headaches when working with large repos The problem I wanted to solve was simple: why do we keep paying for thousands of "junk" tokens — code that has absolutely nothing to do with the question being asked? RepoBrain works by indexing the codebase, understanding the project structure, and only injecting the relevant parts into context for each query. Fewer tokens, more accurate answers. This is the first time I've built something with a measurable, concrete impact — and honestly, that feeling hits differently compared to projects that were just "good enough to ship" 😄 — 🚀 And there's more — v1.3 Early Access is ready. A few things landing in this version: 🚦 Agent Safety Gate — returns SAFE / WARN / BLOCK before every commit 🧠 Persistent Workspace Memory — annotate files once, surfaces on every future run 🔍 Evidence-Based Confidence Score — every output shows retrieval strength, not just guesses ⚡ Full MCP Server — works live inside Claude Code, Cursor, and Codex Still in private early access. If you want in, just DM me or drop a comment — I'll get back to you personally. Repo: https://lnkd.in/gHk-WE6N #AI #LLM #Developer #RepoBrain #CostOptimization #BuildInPublic #OpenSource #GitHub

Developers are constantly seeking ways to streamline their workflows and make the most of their time. In the realm of LLM and agent workflows, teams often struggle to balance reliability and power. Most rely on cumbersome server-side solutions that are difficult to scale and maintain. This is where ComposioHQ/awesome-codex-skills comes in – a curated list of practical Codex skills for automating workflows across the Codex CLI and API. At its core, this repository provides a collection of Python-based skills that can be used to improve the reliability and efficiency of agent behavior. What stands out is the variety of skills available, including bernstein – a multi-agent orchestrator with Codex CLI adapter, and what Are Codex Skills? – a fundamental question that gets to the heart of how these skills work. What makes this repository particularly interesting is how it addresses a common pain point in the development process. By providing a list of practical skills that can be easily integrated into existing workflows, ComposioHQ/awesome-codex-skills makes it easier for developers to make agent behavior more reliable, not just more powerful. Here are some key highlights: - bernstein – Multi-agent orchestrator with Codex CLI adapter. Runs parallel Codex agents in isolated git worktrees with quality gates. - what Are Codex Skills? - a curated list of practical Codex skills for automating workflows across the Codex CLI and API. - built with Python The traction makes sense: a repository sitting at #3 with around 637 new stars in the current trending window is usually solving a problem people can feel immediately. With its focus on making fast-moving AI workflows easier to steer and reuse in real projects, it's no wonder that ComposioHQ/awesome-codex-skills is getting attention. Repo: https://lnkd.in/eTmpF-UT #GitHub #OpenSource #GitHubTrending #LinkedInForDevelopers #Python #AwesomeCodexSkills #Awesome #AwesomeLists

I spent years optimizing/implementing automation scripts... Then I discovered Skills ✨🤖 The difference? Tools/Scripts are for machines 🛠️: "Call this API, parse this JSON, handle error code 422." Skills are for intelligence 🧠: "Here's what success looks like. Figure out the rest." OpenClaw and Claude Code for example proved that a well-written SKILL.md⚡ beats 500 lines of Python, not because it's shorter, but because it adapts when APIs change, edge cases emerge, or requirements shift overnight. How does it work? It uses a ReAct loop 🔄 (Reasoning + Acting): the LLM dynamically selects tools, observes results, and iterates until it reaches the goal. There are a lot of technical details like token optimization, SKILL loading and open AgentSkills specs, but the concept is simple: ✨SKILL.md✨ text file with clear instructions replaces rigid automation code. 🚀This is the shift from Software Engineering 1.0 (explicit control) to 2.0 (intent-based delegation). 🤔Which automation are you maintaining today that you should be describing instead? #AIAgents #OpenClaw #LLM #Automation #SoftwareEngineering #AgenticAI #GenAI #DevOps #DeveloperProductivity #FutureOfCoding #ClaudeCode

The biggest risk in software right now isn’t downtime. It’s letting AI coding agents quietly erode your architecture one "fix" at a time. When an LLM gets stuck, it usually doesn’t stop and ask: - “Should this layer even know about that one?” - “Is this dependency direction allowed?” - “Are we introducing a circular dependency here?” It just makes the code work. So routers start importing database code directly. Service layers begin depending on framework internals. Circular dependencies creep in. And six weeks later the codebase still “runs”, but nobody wants to touch it anymore. That’s exactly why I built ArchUnitPython. It lets you enforce architectural rules in Python projects by writing them as simple unit tests. So instead of *hoping* humans or LLMs respect your architecture, you can make those rules executable and enforce them in CI. Example: rule = (     project_files("src/")     .in_folder("**/presentation/**")     .should_not()     .depend_on_files()     .in_folder("**/database/**") ) assert_passes(rule) A few things it can do: - enforce dependency direction rules - detect circular dependencies - validate naming conventions - validate PlantUML diagrams against code - calculate architecture/code quality metrics - support custom rules (- special support for FastAPI and Django) The goal is simple: If your team has architectural decisions, they should live in tests, not just in wiki pages, PR comments, or one senior engineer’s head. By putting them in your CI/CD pipeline as tests, they are ensured forever. Feedback and PRs are highly welcome! Repo: https://lnkd.in/dMGDBGkP #Python #SoftwareArchitecture #OpenSource #Testing #FastAPI #Django #Pytest #CodeQuality #AIEngineering #LLM

Shipped ShipIt-agent v1.0.0 An open-source Python agent runtime for building powerful, production-style agents with a clean API. What’s in it: - Multiple LLM support - AWS bedrock/OpenAI / Anthropic / Gemini / Groq / Together / Ollama via adapters - prebuilt tools for web search, open URL, workspace files, code execution, memory, planning, verification, artifacts, AskUser, human review - MCP support for remote tool discovery and tool execution - connector-style tools for Gmail, Google Calendar, Google Drive, Slack, Linear, Jira, Notion, Confluence, and custom APIs - session history, memory stores, trace stores, and structured streaming packets - notebook test flows for no-tools, multi-tools, MCP, connectors, AskUser, HILT, streaming, and reasoning Built so you can do things like: - create an agent with llm, tools, mcps, prompt, history - stream live runtime events and tool packets - plug the agent into chat products or internal workflows - inspect reasoning with visible planning / decomposition / synthesis / decision tools GitHub: https://lnkd.in/dpUiYqzF #python #ai #llm #agents #mcp #opensource #bedrock #toolcalling