Tested Orbis in Docker: psf/requests (35 modules) makes a clean 3D graph, expressjs/express (98 modules) collapses into one giant sphere. Notes on what tree-sitter actually captures for code-review prep.
Went through Thariq's 20 HTML examples for practical Claude Code use. Throwaway editing UIs for ticket triage and annotated code diffs stood out. The deciding factor is whether the output's reader is human or AI.
Vektor Memory v1.5.4 supersession chains positioned against YourMemory decay, Cloudflare key-overwrite, and CTX, with a BM25 vs cosine threshold trap and a 5-field minimum schema for agent memory.
uv 0.9.21 as the entry for small Claude SDK Python experiments: uv init, uv add, uv run, uv.lock keep agent projects reproducible across machines and Codex/Claude Code sessions. Operational notes, not a benchmark of the DEV article's uv 0.11.11.
The paper argues that RAG, vector stores, and scratchpads are retrieval, not learning. Read alongside CTX and OCR-Memory, the gap between 'better search' and 'weight-level learning' becomes concrete.
Connecting a DEV article on context rot, Anthropic's 1M context guidance, and Chroma's context rot research with earlier CTX and Compresr posts. The places to watch are CLAUDE.md size, tool output accumulation, and information loss around compact—not the model name.
Tested connecting MCP servers to Ollama local LLMs on M1 Max 64GB. MCPHost is deprecated, tool calling breaks with quantized models, and context fills fast. Includes working TypeScript and Python custom MCP server setups.
Starting from Claude Code's 1.67B token runaway (anthropics/claude-code#4095), this traces why tool responses need is_complete, retryable: false, duplicate detection, and orchestrator-level budget caps. Directly applicable to MCP server design.
A read of CTX, which auto-injects context into Claude Code via the UserPromptSubmit hook. Compared with auto-memory, YourMemory, WUPHF, and Cloudflare Agent Memory on persistence and storage. Also looked at why 1M context still isn't enough and how each agent architecture uses its window differently.
A read of arXiv:2604.26622 OCR-Memory. It renders agent execution history into images, uses Set-of-Mark to let a VLM pick relevant segments, then retrieves verbatim text from the original logs.
Anthropic released Claude Opus 4.7 on April 16, 2026. The staged rollout adds an xhigh effort tier, self-verification before returning, and roughly 3x higher-resolution image input, while intentionally capping cyber capability under Project Glasswing.
