Marcus Rivera
Full-stack developer and open-source advocate. Writes about developer tools, frameworks, and the craft of software.
54 articles
Ollama: Run Local LLMs Like a Pro in 2026
A hands-on guide to Ollama, the default local-LLM runner in 2026 (v0.30.10). Covers install, pulling and running models, calling them from the OpenAI SDK at localhost:11434, structured JSON outputs, tool calling, and Modelfiles, plus how to size a model to your hardware.
By Marcus Rivera · 6 min · Jun 25, 2026
OpenCode: The Open-Source AI Coding Agent at 178K Stars
OpenCode is an open-source (MIT), terminal-native AI coding agent with 178K GitHub stars. It is model-agnostic, connecting to 75+ providers (Anthropic, OpenAI, Google, Ollama) with bring-your-own keys. LSP integration feeds compiler diagnostics back to the model; built-in build and plan agents plus a general subagent. Runs locally/air-gapped, ships frequently (v1.17.9, 826 releases), and now has a desktop beta. Trade-offs: a terminal learning curve, you pay your own API bills, and quality depends on the model you plug in.
By Marcus Rivera · 5 min · Jun 24, 2026
CodeRabbit: The AI Code Reviewer That Reads Your Whole Repo
CodeRabbit is an AI code reviewer that posts line-by-line PR feedback across GitHub, GitLab, Azure DevOps and Bitbucket. Plans run Free, Pro (4/user/mo), Pro Plus (8) and Enterprise, billed only for developers who open PRs. Strengths: context via MCP, one-click autofix, deep static analysis. Watch the 5/10/12 review rate limits.
By Marcus Rivera · 6 min · Jun 23, 2026
Structured Outputs: Force LLMs to Return Valid JSON
A practical guide to OpenAI Structured Outputs: the difference from JSON mode, function calling vs response_format, strict schema rules, constrained decoding, limits, and cross-provider options.
By Marcus Rivera · 8 min · Jun 22, 2026
Google Antigravity 2.0: From Cursor Clone to AI Agent Platform
A hands-on review of Google Antigravity 2.0: its multi-agent orchestration, pricing, and trade-offs.
By Marcus Rivera · 5 min · Jun 20, 2026
Context Engineering: A Practical Playbook for Reliable AI Agents
Context engineering is the discipline of curating tools, prompts, retrieval, and memory each turn so AI agents stay reliable over long-horizon tasks.
By Marcus Rivera · 7 min · Jun 16, 2026
Prompt Caching: How to Cut LLM API Costs by Up to 90%
Prompt caching stores the computed KV attention tensors for a repeated prompt prefix so the model skips recomputation, cutting input cost and latency. Anthropic (explicit cache_control, ~90% read discount), OpenAI (automatic, 50% off, 1,024-token minimum), and Google Gemini (implicit plus explicit cache objects, up to 90%) all support it. The one rule that determines hit rate: put all static content at the front of the prompt and all dynamic content at the back.
By Marcus Rivera · 7 min · Jun 12, 2026
Firecrawl: Turn Any Website Into Agent-Ready Markdown
Firecrawl converts messy, JavaScript-rendered websites into clean, LLM-ready markdown for RAG and AI agents. Install with 'pip install firecrawl' and use the Firecrawl class: scrape for known URLs (1 credit), crawl for discovery (1 credit per page, always set a limit), and schema-based extraction for typed JSON. Watch Enhanced/Stealth Mode, which costs 5 credits per page on Cloudflare-protected sites, and note that credits do not roll over.
By Marcus Rivera · 5 min · Jun 10, 2026
RAG Grounding: 7 Ways to Stop LLM Hallucinations in Production
A practitioner's guide to grounding retrieval-augmented generation systems. Covers fixing retrieval first, hybrid dense-plus-keyword search, cross-encoder reranking, contextual compression, refusal prompting, verified citations, Chain-of-Verification, confidence-threshold abstention, and measuring faithfulness with RAGAS.
By Marcus Rivera · 6 min · Jun 9, 2026
MCP Security: A 2026 Hardening Playbook After CVE-2025-6514
A practical 2026 security playbook for Model Context Protocol agents. It explains MCP-specific threats (prompt injection, tool poisoning, rug pulls, confused-deputy), dissects the critical CVE-2025-6514 mcp-remote RCE, and gives concrete hardening steps: patch to 0.1.16, enforce OAuth 2.1 over HTTPS, isolate servers, gate destructive actions, and audit agent activity.
By Marcus Rivera · 7 min · Jun 2, 2026
AGENTS.md: Configure AI Coding Agents That Actually Obey
AGENTS.md is a Linux Foundation-stewarded open standard, adopted by 60,000+ repositories and read natively by 20+ tools including Codex, Cursor, and Copilot. This guide covers the eight core sections, the phrasing patterns that change agent behavior, monorepo nesting, and how it differs from CLAUDE.md, .cursorrules, MCP, and SKILL.md.
By Marcus Rivera · 9 min · May 31, 2026
Prompt Injection: A 2026 Defense Playbook for AI Agents
A defense playbook for prompt injection in AI agents. It explains why the attack is unsolvable at the model layer, frames the threat with Simon Willison's lethal trifecta (private data, untrusted content, external communication), and prescribes layered controls: architectural separation, least-privilege tools, input filtering, egress allowlisting, circuit breakers, and hardened models, which can cut attack success from 73.2% to 8.7%.
By Marcus Rivera · 6 min · May 30, 2026
Kanwas: The Open-Source AI Workspace That Hit #1 on Product Hunt
Kanwas is an open-source AI workspace enabling human-AI collaboration on a shared canvas.
By Marcus Rivera · 5 min · May 29, 2026
Understand-Anything: The 37K-Star Knowledge Graph for Your Codebase
Understand-Anything converts any codebase into a navigable knowledge graph for easier comprehension.
By Marcus Rivera · 5 min · May 28, 2026
Tycoon AI Review: One Operator, an AI CEO, and a Full C-Suite
Tycoon AI provides solo founders with an AI CEO, Astra, and a full virtual C-suite.
By Marcus Rivera · 6 min · May 25, 2026
Emdash: The Open-Source IDE Built to Run 22 Coding Agents in Parallel
Emdash is an open-source IDE that runs 22 coding agents in parallel for enhanced development.
By Marcus Rivera · 7 min · May 24, 2026
Pipali: The Open-Source Desktop AI Coworker From Khoj AI's YC Team
Pipali is Khoj AI's open-source desktop AI coworker, integrating with your files and apps, supporting multiple LLMs.
By Marcus Rivera · 7 min · May 20, 2026
mattpocock/skills: The 91.7K-Star Repo Reshaping AI-Assisted Engineering
Matt Pocock's 91.7K-star 'skills' repo on GitHub provides solutions to common failures in Claude Code.
By Marcus Rivera · 6 min · May 19, 2026
Raindrop Workshop: The Local AI Agent Debugger That Hit 473 Stars
Raindrop Workshop is an open-source local AI agent debugger, streaming token calls and enabling Claude Code evaluations.
By Marcus Rivera · 6 min · May 18, 2026
OpenHuman: The 776-Star Agent That Reads You Before You Type
OpenHuman is a trending AI agent that anticipates user input, featuring a Memory Tree and numerous integrations.
By Marcus Rivera · 8 min · May 17, 2026
Kilo Code v7: The Open-Source AI Agent Rebuilt for Parallel Work
Kilo Code v7 is an open-source AI agent rebuilt for parallel coding, offering subagents and multi-model comparison.
By Marcus Rivera · 5 min · May 16, 2026
Wispr Flow Review: $15 Voice App Eyeing $2B Valuation
Our Wispr Flow review covers the AI dictation app's high accuracy across platforms and its cloud-only limitations.
By Marcus Rivera · 6 min · May 15, 2026
Vercel Open Agents: Background Coding Agents You Can Fork
Vercel Open Agents provides forkable, sandbox-isolated background coding agents with GitHub integration and PR creation.
By Marcus Rivera · 6 min · May 14, 2026
GitHub Spec-Kit: The 90K-Star Antidote to Vibe-Coding With AI Agents
GitHub's Spec-Kit provides AI coding agents with structured specs, ending 'vibe-coding'.
By Marcus Rivera · 5 min · May 13, 2026
OpenClaw: 371K Stars, Three Rebrands, and a $16M Crypto Scam
OpenClaw, a self-hosted AI agent, saw rapid growth amidst rebrands and a crypto scam.
By Marcus Rivera · 7 min · May 12, 2026
FlowMarket: The Live Network Where AI Agents Negotiate B2B Deals
FlowMarket enables AI agents to autonomously find and negotiate B2B deals in a live network.
By Marcus Rivera · 7 min · May 8, 2026
Cursor Bugbot Hits 78% Bug Resolution by Learning From Your PRs
Cursor Bugbot resolves 78% of bugs by learning from merged PRs, outperforming rivals.
By Marcus Rivera · 7 min · May 7, 2026
Gemini API Webhooks: Kill the Polling Loop on Long-Running Jobs
Google's Gemini API Webhooks eliminate polling loops for long-running jobs, simplifying integration.
By Marcus Rivera · 5 min · May 6, 2026
Postiz: The 29.6K-Star Open-Source Social Scheduler Killing Buffer
Postiz is a popular open-source social scheduler, offering a Buffer alternative with AI agent capabilities.
By Marcus Rivera · 6 min · May 4, 2026
VibeVoice: Microsoft's Open-Source Frontier Voice AI Hits 33K Stars
Microsoft's VibeVoice is an open-source voice AI offering advanced ASR and TTS capabilities.
By Marcus Rivera · 7 min · May 2, 2026
Windsurf 2.0: Cognition Bakes Devin Right Into the IDE
Windsurf 2.0 integrates Cognition's Devin AI agent directly into the IDE for seamless management.
By Marcus Rivera · 7 min · Apr 30, 2026
Nemotron 3 Nano Omni: NVIDIA's 30B Open Model Sees and Hears
NVIDIA's Nemotron 3 Nano Omni is a 30B open multimodal model, processing diverse data with high throughput.
By Marcus Rivera · 6 min · Apr 29, 2026
Archon OS: The Open-Source Brain That Makes Claude Code Remember
Archon OS is an open-source knowledge backbone that helps AI coding assistants remember information.
By Marcus Rivera · 6 min · Apr 21, 2026
Goose: Block's Open-Source Local-First AI Agent Hits 35K
Block's open-source, local-first AI agent, Goose, gained 35K stars and joined the Linux Foundation.
By Marcus Rivera · 5 min · Apr 20, 2026
ElevenCreative Review: ElevenLabs' All-in-One AI Studio
ElevenCreative by ElevenLabs combines all AI content creation tools into one platform.
By Marcus Rivera · 6 min · Apr 19, 2026
Voicebox: The Local-First Voice Cloning Studio for Mac and Windows
Voicebox is a local-first, open-source voice cloning studio for Mac and Windows, built on Qwen3-TTS.
By Marcus Rivera · 7 min · Apr 18, 2026
NVIDIA Ising: Open-Source AI Models That Make Quantum Computing Actually Work
NVIDIA Ising offers open-source AI models to improve quantum error correction, making quantum computing more effective.
By Marcus Rivera · 6 min · Apr 17, 2026
GLM-5.1: The Open-Source 754B Model That Works for Eight Hours Straight
Z.ai's GLM-5.1 is an open-source 754B model that runs autonomously for eight hours, enhancing AI agents.
By Marcus Rivera · 5 min · Apr 15, 2026
Caveman: The Claude Code Skill That Cuts 65% of Output Tokens
Caveman, a Claude Code skill, dramatically cuts AI output tokens by 65%, optimizing agent interactions.
By Marcus Rivera · 5 min · Apr 15, 2026
Ghost Pepper: 100% Local Speech-to-Text for macOS
Ghost Pepper offers secure, 100% local speech-to-text and transcription for macOS on Apple Silicon.
By Marcus Rivera · 5 min · Apr 15, 2026
Edgee Codex Compressor: The Rust Gateway That Cuts Codex Costs 35.6%
Edgee Codex Compressor, a Rust gateway, cuts LLM costs by 35.6% by compressing tool output.
By Marcus Rivera · 4 min · Apr 12, 2026
Ray: The Open-Source AI Financial Advisor That Runs on Your Laptop
Ray is an open-source AI financial advisor that runs locally, securing your data while connecting to banks.
By Marcus Rivera · 4 min · Apr 12, 2026
Hermes Agent: The Open-Source AI Agent That Learns How You Work
Hermes Agent is an open-source AI that learns your workflow with persistent memory and skill creation.
By Marcus Rivera · 4 min · Apr 12, 2026
Cohere Transcribe: The Open-Source ASR Model That Dethroned Whisper
Cohere Transcribe, an open-source ASR model, dethrones Whisper with superior accuracy and speed.
By Marcus Rivera · 5 min · Apr 11, 2026
Baton: The Desktop App for Orchestrating AI Coding Agents
Baton is a desktop app for developers to orchestrate, monitor, and review multiple AI coding agents.
By Marcus Rivera · 4 min · Apr 10, 2026
Gemini CLI: Google's Open-Source Terminal Agent Hits 101K GitHub Stars
Google's Gemini CLI, an open-source terminal AI agent, hits 101K GitHub stars with new features.
By Marcus Rivera · 4 min · Apr 9, 2026
Google Gemma 4: Four Open Models That Punch Above Their Weight
Google DeepMind's Gemma 4 releases four open-weight models that rank high and run on consumer hardware.
By Marcus Rivera · 4 min · Apr 8, 2026
Moondream 3: The 9B Vision Model That Runs Like a 2B
Moondream 3 is a 9B vision model that runs efficiently like a 2B, offering advanced capabilities.
By Marcus Rivera · 4 min · Apr 1, 2026
Voxtral TTS: Mistral's Open-Weight Speech Model Challenges ElevenLabs
Mistral's Voxtral TTS is an open-weight speech model challenging ElevenLabs with naturalness and voice cloning.
By Marcus Rivera · 4 min · Mar 31, 2026
5 Best AI Tool Directories in 2026: Find the Right Tool Fast
Compare the top 5 AI tool directories to quickly find the best AI tools for your needs.
By Marcus Rivera · 7 min · Mar 30, 2026
Mistral Small 4: One Open-Source Model Replaces Three Separate AI Products
Mistral Small 4 unifies three AI products into one powerful open-source model, simplifying capabilities.
By Marcus Rivera · 4 min · Mar 30, 2026
LTX 2.3: Lightricks' Open-Source Model Generates 4K Video with Synced Audio
Lightricks' LTX 2.3 is an open-source model generating native 4K video with perfectly synced audio.
By Marcus Rivera · 6 min · Mar 29, 2026
Biome v2.4: The Rust-Powered Toolchain Replacing ESLint and Prettier
Biome v2.4, a Rust toolchain, is replacing ESLint and Prettier with faster, more efficient performance.
By Marcus Rivera · 6 min · Mar 29, 2026
OpenClaw: The Self-Hosted AI Agent That Hit 247K GitHub Stars
OpenClaw, a self-hosted AI agent integrating with various UIs, quickly became a GitHub sensation.
By Marcus Rivera · 6 min · Mar 29, 2026