Programming

Imp ports DSPy's declarative AI programming to Elixir/BEAM with signatures, optimizers, RAG, and supervision-tree deployment.

A practical comparison of three terminal-based AI coding agents across context windows, sandboxing, benchmarks, and pricing.

A practical guide for developers adding agent capabilities without repeating the security mistakes making headlines this week.

Jev offers typed, calibrated decisions for classification and routing at a fraction of LLM latency and cost.

GPT-6.1 Sol delivers near-Astra performance for coding and agentic workflows at one-fifth the token cost. Here is what changed and who should use it.

MCP is the standard connecting AI agents to external tools. From Tether wallets to Meta connectors, here's how it works and how to build with it.

Anthropic released the Claude Agent SDK alongside Sonnet 4.5 — the same infrastructure that powers Claude Code, now available for your own agents.

Amazon's Strands Harness bundles agent tooling into one environment, with reported token savings up to 77% on some benchmarks.

Coinbase's x402 protocol revives HTTP 402 to let software pay for data feeds and API calls in the same request — no account or human approval required.

OpenAI's GPT-6 Sol and Anthropic's Opus 5.5 launched on the same day. Here is how developers should compare pricing, benchmarks, and use cases.