Relevance Is the Wrong Sort Order for Agent Memory

Semantic recall inherited an assumption from document search that is false for notes. Ranking by similarity drops the very notes that carry the truth of a correction.

Read →

Agents Never Remember What Isn't There

Every agent memory system stores what was found. The expensive half of any session is what was looked for and not found, and that is the half no memory can carry.

Read →

Agent Memory Expiry Is a State, Not a Delete

Most agent-memory systems age notes out with a TTL delete. I shipped that bug myself, then fixed it: expiry should be a visibility state.

Read →

The Sentinel Pattern: A Multi-Agent Dev Loop That Doesn't Trust Its Own Agents

A coder reported nine completed items, the audit said seven, and the nine was already in the ledger. The loop that failure produced: one gatekeeper that writes no code, disposable coders in isolated worktrees, and the arithmetic that caps how many are worth running.

Read →

The Agent Never Chooses to Remember: Memory as a Harness Property

Every shipped agent memory design assumes the model decides to save and recall; in a seeded control run it decided zero times in 114 turns, which is why the load-bearing tier has to be delivered by the harness rather than fetched by the agent.

Read →

Your MCP Tool Works. The Model Still Won't Call It.

A controlled study of MCP tool adoption: 0 calls in 63 turns with 30 mentions of the tool, zero in 114 turns with the answers already in the store — and the harness injection that flipped it.

Read →

I Deleted Every Ranking Heuristic From My Code Search Engine

3,817 lines of query-side if/else, deleted in one commit — with the measured evidence for why keyword branches can never rank code search, and the two index-time priors that separated canonical from look-alike.

Read →

Embedding Dilution: Why Semantic Code Search Misses the Answer

The target function's docstring paraphrased my query almost word for word, yet it ranked below 200 look-alikes — because everything else in the chunk averaged it away. A measured post-mortem, and the dual-vector fix it shipped.

Read →

What Actually Survives /compact in Claude Code: An Empirical Map

We forced 100+ compactions across two instrumented runs and graded, fact by fact, what the boundary keeps and what silently dies — with the survival curve, the confabulation, and the honest costs.

Read →

The Four Families of Context Relief for LLM Coding Agents

Eviction, offload-and-recall, retrieval-over-stuffing, and subagent isolation — the four ways to keep a coding agent from drowning in its own context, and why they only work when composed.

Read →

Building Vectr, Part 3: What the Benchmark Numbers Actually Mean

How I benchmarked an AI code editor tool without fooling myself — the research vs implementation distinction that makes a +19% headline misleading, the 5 of 6 CPython tasks where re-discovery dropped, and the limitations that decide whether any of it applies to you.

Read →