DeepSeek released Harness, an MIT-licensed agent framework built on the Cordis plugin kernel, into developer preview. The framework treats every agent capability as a plugin, enabling model, tool, and…
Camel AI launched Stream, a flat-rate API service offering unlimited access to DeepSeek V4 Flash (0731) for coding agents, priced at a fixed monthly fee with no token metering or overage charges. The …
A developer team improved the coding performance of 15 large language models in one afternoon by changing only the edit tool in their harness, not the models themselves. The team found that edit forma…
A developer's Claude 3.5 Sonnet MCP setup failed last Thursday due to oversized database schema responses exceeding context limits, causing timeouts and JSON parse errors. The developer fixed it by wr…
A developer has released phi, a 12 MB terminal coding agent written in Go that supports any OpenAI-compatible or Anthropic-native model via a pluggable config. The tool features read-only defaults, ha…
A comprehensive review by developers who daily-drove seven AI coding tools across production codebases finds Cursor remains the best all-around pick for most developers, while Claude Code excels as a …
DevTools Review's pricing research across 11 AI coding tools shows prices ranging from $0 for free tiers (Cline, Aider, Zed, Cody) to $200/month for high-end agentic plans (Cursor Ultra, Windsurf Max,…
Code retrieval is shifting from embeddings to graph-based approaches, as demonstrated by the trending open-source tool code-graph-rag, which parses repositories with Tree-sitter, builds a knowledge gr…
A new open-source bash harness lets developers benchmark AI coding agents Claude Code 2.1, Aider 0.86.1, and the Cursor CLI (binary named `agent`) on their own repositories, scoring each attempt with …
AliceLabs LLC launched MarketNow, an npm registry hosting 9,248 MCP servers for AI agents like Claude Desktop, Cursor, Cline, Continue, and Aider, with 43 free skills and paid options from $0.99 to $9…
APC and APX, two components of a portable agent project, separate portable context from runtime availability. APC stores project contracts in the repository, while APX detects local runtimes via `apx …
Husk, a desktop workspace for terminal AI agents, wraps tools like Claude, Copilot, Codex, and Aider in an Electron window with a real PTY, drag-drop file context, voice output, session resume, and a …
Kimi's k3 model now runs on a single consumer GPU, achieving 113.83 tok/s on a 32 GB RTX 5090 after being shrunk to 28.8 GB from its original 48B size. The model works with coding agents like Claude C…
OpenCode, an open-source coding agent, can now run entirely locally using QVAC, an SDK and CLI from Tether that serves models on-device across GPU backends. The setup eliminates cloud dependencies, gi…
Codex and Claude Code are AI coding agents built on opposite philosophies: Claude Code favors supervised depth and asks before risky changes, while Codex favors delegation and async execution in a san…
A developer built a local proxy in Rust that acts as a circuit breaker for AI coding agents, intercepting every LLM request and tool payload to enforce budget and security rules in real time. The prox…
A developer built an AI Skill that generates production-ready GitHub Actions workflows with zero configuration errors. The skill enforces 12 quality gates, 5 decision templates, and 3 mandatory securi…
Bohay, a free and open-source terminal tool for orchestrating AI coding agents, launched on Hacker News. The tool provides a single interface to run, watch, resume, and manage multiple agents, with fe…
Cursor costs $20 per month and GitHub Copilot costs $10 per month, both scoring 57% crowd approval, but solo developers on a tight budget have two free open-source alternatives: Cline and Aider, where…
Kimi has launched 'Kimi Everywhere', a kit that lets developers run any coding harness—including Claude Code, Codex, OpenCode, Cline, and Aider—on a single flat-fee Kimi Code subscription ($19+/mo). T…