SmallDocs, a new command-line tool that creates lightweight, private documents for coding agents, launched to integrate with AI assistants like Claude, Codex, and Cursor. The tool renders Markdown fil…
Newer Anthropic Claude models, including Opus 4.8 and Sonnet 5, are generating malformed tool calls for Pi's custom edit tool by inventing extra fields, a problem absent in older models. Armin Ronache…
A developer distinguishes three layers of the AI agent stack through open-source projects: Pi as an agent kernel and toolkit, Goose as a local agent workbench, and OpenCode as a coding-first software-…
OpenAI now allows ChatGPT Plus subscribers to use their $20/month plan inside third-party coding agents like Pi and OpenCode, effectively providing $100–$200 worth of tokens. However, the policy is no…
ConductorOne released agent-tui, an open-source tool that gives terminal applications a queryable DOM-like interface for AI agents. The tool runs programs on a PTY, exposes rendered screens as text wi…
Commonplace launches a self-hosted, privacy-tiered memory system for AI agents, using a two-tier Graphiti knowledge graph that runs entirely on local hardware by default, with a personal tier optional…
Bb, a new MIT-licensed IDE for loop-driven development, orchestrates coding agents and automations locally on the user's machine, supporting Claude Code, Codex, Cursor, and Pi. It runs on existing pro…
Looop, a new open-source tool, launches as a tiny, portable autonomous control loop for LLM agents, operating as a single binary without external dependencies. It monitors sources like GitHub and Line…
Ouijit, an open-source terminal-based coding agent orchestrator, launched on Hacker News. The tool provides sandboxed task execution via Lima VMs, session-scoped CLI awareness for agents, and lifecycl…
Framein, a local work-state layer for AI agents, launched to keep task context across Claude, Codex, and Gemini. The tool maintains a shared contract, decision trail, and validation results, enabling …
DeepSeek V4 Flash, a 284-billion-parameter Mixture-of-Experts model, now runs locally on a 128GB MacBook Pro via antirez's experimental llama.cpp fork, achieving ~21 tokens/sec generation on the Metal…
Uber capped employee AI coding tool spending at $1,500 per month in June 2026 after burning through its entire 2026 budget in four months, with Claude Code adoption surging from a third of engineers t…
DeepReinforce released Ornith-1.0, a family of self-scaffolding LLMs for agentic coding built on Gemma 4 and Qwen 3.5, achieving state-of-the-art performance among open-source models of comparable siz…
Sidequest, a new extension for the Pi AI agent, provides a side channel for context-aware questions without disrupting the main conversation. It offers threaded, persistent, and tool-capable interacti…
Tau is an educational Python coding agent designed to teach how agents are built by exposing every component—provider adapters, harness, coding environment, and terminal UI—in readable layers. The pro…
Role-model, an open protocol for capability-aware AI routing, has been released with a packaged reference runtime that routes requests based on role, task, capability, and policy rather than model nam…
Developer launches role-model, a routing protocol and runtime for hybrid local/cloud AI, enabling deterministic request routing with fallback to a controller model. The system assigns domains and role…
Developer Scott Spencer released My-Pi Coding-Agent, a curated distribution of the Pi coding agent CLI with prewired extensions including MCP, LSP, skills, recall, redaction, telemetry, team mode, and…
A developer outlines a phased approach to onboarding AI coding agents onto existing projects, arguing that poor agent performance often stems from insufficient project documentation rather than model …
Vercel released AI SDK 7, a major update to its TypeScript SDK for building AI applications, adding production-grade features for agent development, including reasoning control, tool context, runtime …