Leela Kumili writes about DoorDash's Flux platform, which moved LLM-based coding agent workloads from developer laptops to cloud infrastructure, automating 130,000 engineering tasks in a single month and supporting over 25,000 automated code reviews per week. The platform was built after local execution hit limits on power, uptime, and security, and is organized around four primitives: Firecracker microVM sandboxes, an in-house MCP gateway, YAML-defined playbooks, and multiple invocation surfaces (Slack, GitHub, cron, CLI, conversational interfaces).
- Sandboxes achieve a 95th percentile SLO under 5 seconds for full setup, including microVM start, repo clone, build tool install, and agent harness configuration.
- Playbooks can mix agent-driven steps with deterministic code where predictable execution or validation is required.
- The Agent Gateway enforces scoped permissions and logs all agent activity for auditing and policy enforcement.
- DoorDash switched Slack integration from private channels to public threads so engineers could observe agent executions and see how other teams delegated work.
- Sandboxes achieve a 95th percentile SLO under 5 seconds for full setup, including microVM start, repo clone, build tool install, and agent harness configuration.
- Playbooks can mix agent-driven steps with deterministic code where predictable execution or validation is required.
- The Agent Gateway enforces scoped permissions and logs all agent activity for auditing and policy enforcement.
- DoorDash switched Slack integration from private channels to public threads so engineers could observe agent executions and see how other teams delegated work.
Mashrul Haque writes about using git worktrees to run multiple LLM coding agents in parallel, each on its own branch and isolated directory, eliminating the bottleneck of sequential agent sessions. He demonstrates a 5-agent workflow with Claude Code on a .NET/Blazor project, reporting roughly 5x throughput gains over single-agent sequential work.
- Boris Cherny, Creator and Head of Claude Code at Anthropic, calls worktrees his number one productivity tip and runs 3'' 5 simultaneously
- Claude Code ships a built-in `--worktree` (`-w`) flag that auto-creates an isolated worktree per session
- Boris Cherny, Creator and Head of Claude Code at Anthropic, calls worktrees his number one productivity tip and runs 3'' 5 simultaneously
- Claude Code ships a built-in `--worktree` (`-w`) flag that auto-creates an isolated worktree per session
SWE-bench Verified is a human-filtered subset of 500 instances from SWE-bench created in collaboration with OpenAI to provide a reliable evaluation set for coding agents and language models. Human annotators reviewed each instance to ensure problem descriptions are clear, test patches are correct, and tasks are solvable with available information. The Verified leaderboard shows results from a wide variety of AI coding systems, and a Bash Only view isolates language model performance using mini-SWE-agent in a minimal bash environment.
- Human validation ensures clarity, correctness of test patches, and solvability
- Bash-only comparison uses mini-SWE-agent with ReAct loop, no tools or scaffold
- Leaderboard distinguishes mini-SWE-agent LM results from full agent systems via Agent dropdown
- Release 2.x uses tool calling vs 1.x parses actions from output strings, making releases not directly comparable
- Human validation ensures clarity, correctness of test patches, and solvability
- Bash-only comparison uses mini-SWE-agent with ReAct loop, no tools or scaffold
- Leaderboard distinguishes mini-SWE-agent LM results from full agent systems via Agent dropdown
- Release 2.x uses tool calling vs 1.x parses actions from output strings, making releases not directly comparable
MindMux presents brain.md, an open-source toolkit that provides a persistent memory layer for coding agents by storing project knowledge as plain Markdown files within a repository. This system ensures that critical decisions and constraints are durable across different LLM sessions and machines via version control. A zero-dependency CLI manages the reading and writing of these files to maintain data integrity through an append-only timeline.
- Uses Markdown instead of databases like SQLite to facilitate easier diffing in git history.
- Features a "correct by construction" design that prevents malformed edits by making the CLI the exclusive writer.
- Supports integration with several agents including Claude Code, Codex, Cursor, and Pi.
- Uses Markdown instead of databases like SQLite to facilitate easier diffing in git history.
- Features a "correct by construction" design that prevents malformed edits by making the CLI the exclusive writer.
- Supports integration with several agents including Claude Code, Codex, Cursor, and Pi.
Anurag Singh writes that Cursor’s strength is its capacity for deep project understanding through efficient context management rather than simple model speed. Instead of pushing a whole repository into an LLM's window, the IDE employs search tools to provide only relevant code segments as tasks arise. This curated approach ensures models receive high-quality information and instructions tailored to their specific capabilities, allowing them to maintain existing architectural patterns more effectively.
* The tool uses Instant Grep via a local text index instead of scanning every file from scratch.
* Cursor is significantly more effective in complex or large projects where it can identify and reuse established implementations.
* Its search ability helps prevent the common problem of generating redundant helper functions that already exist within the codebase.
* The tool uses Instant Grep via a local text index instead of scanning every file from scratch.
* Cursor is significantly more effective in complex or large projects where it can identify and reuse established implementations.
* Its search ability helps prevent the common problem of generating redundant helper functions that already exist within the codebase.
The author explains how enabling the built-in sandbox feature in Claude Code has transformed their productivity by allowing for an autonomous workflow. By activating auto-allow mode via the /sandbox command, users can permit AI agents to execute repetitive tasks like running tests or installing dependencies without needing constant manual approval for every individual command, which reduces mental overhead and time spent waiting on prompts.
- Claude Code provides a built-in sandbox that uses macOS Seatbelt on Mac and Bubblewrap on Linux/WSL2.
- The environment restricts file writing primarily to the current project directory and temporary session files.
- Network access is controlled, requiring manual approval when the agent attempts to connect to a new domain.
- For maximum security and complete isolation from a system, using Docker containers or virtual machines remains more robust than the built-in sandbox features.
- Claude Code provides a built-in sandbox that uses macOS Seatbelt on Mac and Bubblewrap on Linux/WSL2.
- The environment restricts file writing primarily to the current project directory and temporary session files.
- Network access is controlled, requiring manual approval when the agent attempts to connect to a new domain.
- For maximum security and complete isolation from a system, using Docker containers or virtual machines remains more robust than the built-in sandbox features.
A distillation of the Claude Fable 5 workflow into actionable skills designed to guide AI agents through a systematic think, act, and prove methodology. The framework improves agentic reliability by enforcing specific sequences like classifying tasks, gathering parallel evidence from primary sources, making surgical edits rather than broad changes, and undergoing adversarial verification via an automated judge. It includes specialized domain adapters for sectors such as coding, research, marketing, and DevOps to tailor the reasoning process to specific professional requirements. The method is specifically designed to mitigate common LLM failures like reward hacking, silent code errors in tests, and false claims of task completion.
>"Before Fable 5 was deprecated, it wrote down its own problem-solving method. Step by step. How it classifies a task, defines "done," gathers evidence, commits to one recommendation, makes the smallest correct change, verifies by observation, and reports the outcome honestly."
- Core skills: fable-method (thinking), fable-loop (orchestration), fable-judge (verification), and fable-domain (adapter generation)
- Focuses on preventing unauthorized staging or "reward hacking" through strict observation cycles
- Validated against 260+ agent runs using blind LLM judges to verify results via code execution rather than reports
>"Before Fable 5 was deprecated, it wrote down its own problem-solving method. Step by step. How it classifies a task, defines "done," gathers evidence, commits to one recommendation, makes the smallest correct change, verifies by observation, and reports the outcome honestly."
- Core skills: fable-method (thinking), fable-loop (orchestration), fable-judge (verification), and fable-domain (adapter generation)
- Focuses on preventing unauthorized staging or "reward hacking" through strict observation cycles
- Validated against 260+ agent runs using blind LLM judges to verify results via code execution rather than reports
Simon Willison reviews Ornith-1.0, a new series of open-weights models from DeepReinforce designed for agentic coding. Built on Gemma 4 and Qwen 3.5, these models range from 9B to 397B parameters and demonstrate high proficiency in coding benchmarks and tool-use tasks.
- Available in 9B Dense, 31B Dense, 35B MoE, and 397B MoE variants
- Capable of navigating codebases and executing complex tool calls
- Built on Apache 2.0 licensed base models
- Available in 9B Dense, 31B Dense, 35B MoE, and 397B MoE variants
- Capable of navigating codebases and executing complex tool calls
- Built on Apache 2.0 licensed base models
From installing Ollama to launching OpenCode with a local model, step by step.
This guide explains how to build a fully local AI coding agent by integrating Ollama, Google's Gemma 4, and OpenCode to ensure data privacy, cost control, and local experimentation. The workflow involves installing Ollama to serve the edge-optimized `gemma4:e4b` model, setting up OpenCode as the agent runtime via npm, and linking them through a local API configuration with a 128K context window. This setup provides a capable, offline development assistant that handles code generation, repository analysis, and file operations without transmitting any data to the cloud.
* **Core Stack:** Uses Ollama for model serving, Gemma 4 (`gemma4:e4b`) as the local LLM, and OpenCode as an open-source agent interface.
* **Setup Steps:** Install Ollama, pull the Gemma 4 model, install OpenCode via `npm install -g opencode-ai`, and connect them by creating a Modelfile for the context window and configuring `opencode.json`.
* **Capabilities:** The local agent supports 128K context, enables coding tasks and workspace automation, and operates entirely offline for maximum security.
This guide explains how to build a fully local AI coding agent by integrating Ollama, Google's Gemma 4, and OpenCode to ensure data privacy, cost control, and local experimentation. The workflow involves installing Ollama to serve the edge-optimized `gemma4:e4b` model, setting up OpenCode as the agent runtime via npm, and linking them through a local API configuration with a 128K context window. This setup provides a capable, offline development assistant that handles code generation, repository analysis, and file operations without transmitting any data to the cloud.
* **Core Stack:** Uses Ollama for model serving, Gemma 4 (`gemma4:e4b`) as the local LLM, and OpenCode as an open-source agent interface.
* **Setup Steps:** Install Ollama, pull the Gemma 4 model, install OpenCode via `npm install -g opencode-ai`, and connect them by creating a Modelfile for the context window and configuring `opencode.json`.
* **Capabilities:** The local agent supports 128K context, enables coding tasks and workspace automation, and operates entirely offline for maximum security.
This article explores the concept of harness engineering, arguing that a functional AI agent is defined not just by its underlying model, but by the scaffolding built around it—including prompts, tools, sandboxes, and feedback loops. The author suggests shifting focus from picking the smartest model to designing robust systems that turn raw models into reliable agents. By treating mistakes as signals for new constraints rather than simple failures, engineers can create a ratchet effect that continuously improves agent performance through better configuration.
Main topics:
- Defining an agent as the combination of a model and its harness
- Reframing model errors as configuration or skill issues
- Using failure history to implement permanent rules via hooks and documentation
- Core primitives including filesystems, bash execution, sandboxes, and memory management
- Managing context rot through compaction and tool offloading
- Achieving long-horizon work through planning, verification, and agent splits
Main topics:
- Defining an agent as the combination of a model and its harness
- Reframing model errors as configuration or skill issues
- Using failure history to implement permanent rules via hooks and documentation
- Core primitives including filesystems, bash execution, sandboxes, and memory management
- Managing context rot through compaction and tool offloading
- Achieving long-horizon work through planning, verification, and agent splits
