Observed Signal · Aug 22, 2026 · Technical Release · Source: DEV Community · Impact: 3/5 · Sentiment: Neutral
Anthropic ships memory into Claude Code
A developer describes building an MCP-based persistent memory layer for AI coding assistants called cachly and how Anthropic's announcement that Claude Code gained a memory feature prompted re-evaluation of that work. The author explains a reproducible test for measuring whether an assistant truly persists facts between sessions, shares benchmark results from a personal corpus, and summarizes community feedback that changed the project's metrics and reliability checks. The post notes cachly offers a free tier hosted in the EU and links to the project's site.
A major LLM provider (Anthropic) added a persistent memory feature to Claude Code, which directly affects external memory solutions and developer choices about building custom assistant memory layers; this is relevant to AI infrastructure but not an industry-shifting platform policy change.
Track Anthropic Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Anthropic shipped a memory feature into Claude Code (described in the release notes as "memory").
- The author built a memory layer for AI coding assistants called cachly that runs over MCP and persists learned facts across restarts and model changes.
- The author published a reproducible test script to measure whether a fact learned in one session is recalled in fresh sessions (a recall ratio test).
- Benchmarking on the author's corpus (499 lessons, 100 questions) showed cachly's ranker returned the correct top-1 answer 40% of the time vs 21% for a words-only baseline, with the correct lesson present in the candidate pool 97% of the time.
- cachly offers a free tier and is hosted in the EU at https://cachly.dev/?utm_source=devto&utm_medium=article&utm_content=the-day-the-vendor-shipped-my-feature.
Connected Companies & Entities
1 Entity mapped“Anthropic shipped memory into Claude Code. Not "context improvements", not "a longer window". The word in the release notes was memory — the...”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Anthropic's Code with Claude: Five Key Updates
Anthropic announced near-term access to the full capacity of SpaceX’s Colossus 1 datacenter, giving the company access to more than 220,000 Nvidia AI chips. The deal follows months of public rivalry — Elon Musk had recently criticised Anthropic — but he said discussions with Anthropic staff left him “impressed,” and xAI has been folded into SpaceX under the name SpaceXAI. Anthropic said it will ramp Claude inference on Colossus 1 within days and earlier developer updates increased user-facing rate limits and API capacity for Claude Code and Opus. The report also notes mutual interest in exploring orbital AI datacenters. Separately, Anthropic remains in dispute with the Pentagon over usage restrictions and is withholding public release of a security-focused model called Claude Mythos Preview that finds long‑hidden software vulnerabilities.
Anthropic Unifies Claude and Cowork Memory
Anthropic announced it has merged the memory systems used by Claude chat and Claude Cowork so information learned in one experience is available in the other. The company now exposes stored memories so users can read, edit, or delete them, and memories are added incrementally during conversations rather than only at the end. By default Claude will exclude certain sensitive categories (health, race, religion, politics, gender identity) unless users opt in via an “include sensitive topics in memory” toggle; it will never save government IDs, Social Security numbers, criminal history, immigration status, or items violating its acceptable use policy. The memory feature is enabled by default across Free, Pro, and Max plans on web, desktop, and mobile (mobile users must update apps).
Anthropic recounts the making of Claude Code
Anthropic published a 'making of' account detailing the technical and product evolution that produced Claude Code, its coding-assistant AI. The company started with a VS Code extension in early 2022 (about 100 external users) and iterated through internal command-line tools (Clide), demos and Claude CLI before launching Claude Code as the successor to Claude CLI in early 2025. Anthropic engineers and leaders quoted include co‑founder and Labs lead Ben Mann, Head of Reinforcement Learning Shauna Kravec, Boris Cherny and Raphael Lee. The piece describes agentic-coding milestones (Function Calling, search tools), cites model roadmaps (Claude Sonnet, Fable and Mythos series) and gives internal adoption anecdotes—e.g., engineers reporting Claude Code authored increasing shares of their code in 2025. The article places Claude Code in competitive context with OpenAI and Google and cites Anthropic data on rising usage of coding agents.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.