[ Category ]
All technical deep dives, system architectures, and AI breakdowns, ordered by date.
Agent Systems & APIsGraphify v0.9.55 turns complex codebases into queryable AST knowledge graphs. By replacing vector embeddings with deterministic syntactic edges, it provides precise multi-hop navigation for Claude Code, Codex, and Cursor via MCP.
Agent Systems & APIsGPT-6 Astra is here in limited preview with general availability set for September 5. It saturates ARC-AGI-3 at 99.9%, posts 57.9% on Terminal-Bench 4.0, and prices at $10/$50 per million tokens, positioning it directly against Anthropic's Claude Fable 5.1 with a credential-gated cyber edge.
Agent Systems & APIsMeta releases Muse Spark 1.3 today in Muse Code and Meta Model API: better collaboration, ~25% fewer tokens and ~20% fewer tool calls on long-horizon coding, stronger prompt-injection robustness, and a stronger bias toward asking before consequential actions, with max reasoning coming after additional safety testing.
Agent Systems & APIsAnthropic released Claude Fable 5.1 and Mythos 5.1, the same model with two safeguard tiers. The developer story is in the details: cache-read pricing cut to $0.25/MTok, breaking changes around forced tool use and thinking blocks, and per-message effort control.
Agent Systems & APIsMoonshot AI retires kimi-k2.5 and the entire context-tiered moonshot-v1 family on August 31. Here's what changes, what the migration to kimi-k3 (2.8T parameters, 1M context) involves, and why it isn't price-neutral.
Agent Systems & APIsAnthropic will permanently raise Claude Code's standard weekly limits by 25% on September 14 — but the temporary 50% boost ends the same day, so heavy users get about 17% less capacity than they have today.
Agent Systems & APIsAnthropic has opened a research preview of the Model Hardware Standard (MHS)—a unified driver and protocol layer allowing AI agents to discover, orchestrate, and safely operate physical laboratory instruments and robotic workcells. Here is an architectural deep dive, real lab benchmarks, and developer implications.
Agent Systems & APIsMistral AI has released Agentic Search and the Mistral Search Toolkit, introducing an active five-tool inspection loop—search, open, navigate, read, grep—that boosts FinanceBench accuracy from 26.7% to 86.0% while slashing token usage by 33.7%.
Agent Systems & APIsThree OpenAI platform products hard-stop on November 30, 2026, and Evals goes read-only a month earlier. Here is what each one maps to, the code to write, and the order to do it in.
Agent Systems & APIsThe initialize handshake and Mcp-Session-Id are gone. Every MCP request now carries its own version, identity, and capabilities — and the August 22 roadmap shows where the protocol goes next.
Agent Systems & APIsAnthropic took four core agent-building blocks to general availability on the Claude Platform and added a new browser use tool. Here's what changed, what it costs, and how to build your first production agent with it.