Glean 拾遗
Recent picks

6picks · chronological

11-14

The five primitives behind always-on agents

Always-on agents are mostly asleep: an event wakes a worker, a short run executes, state is written back, and the agent sleeps again. The post decomposes the surrounding architecture into five primitives. An event inbox (durable table + handler + worker) replaces letting each event source call the agent directly, avoiding competing runs and lost events on crash. Timers split into agent-set follow-ups and recurring schedules, stored separately and fired by a polling scheduler that writes into the inbox. Memory is a directory of files for user instructions, user notes, past messages and task progress, with the rule that memory only holds what cannot be looked up elsewhere. Permissions rely on a credential-injecting proxy, classifier-based auto mode, and deferred tool calls that end a run mid-call and resume it from a new event. An outbox with a dispatcher paces delivery and enables retries. The only hard number is a 78% per-task cost drop on a long-horizon coding benchmark versus 40% on typical workloads.

claude.com · 15 min · Agent Architecture · Agent Infrastructure · Agent-Memory
11-13

Two Agents, One Record: Git-Style Branches Instead of Row Locks

Two agents doing read-modify-write on shared memory lose updates silently: because an agent writes back the whole record it read, a stale save can reset a field another agent just changed, and both report success. The post walks through the three usual fixes—single writer, row locks or optimistic version checks, last-write-wins—and argues all fall short for multi-step tasks spanning several records, since none produces a reviewable diff or an audit trail. It then demos Omnigraph, an MIT-licensed graph database in Rust with a Git-style model: each agent commits to its own branch, merges compare against the merge base, and a stale branch is rejected with divergent_update instead of publishing. The walkthrough uses Claude Code and Codex, covering @key stable IDs, --snapshot reads of old commits, and a Cedar policy with per-agent tokens returning HTTP 403 for writes to main. Useful for anyone building multi-agent shared state, though the headline's 1,000-agent scale is never shown—the demo is one developer and two agents.

x.com · 11 min · Agent Infrastructure · Agent-Memory · Multi-Agent
08-23

Self-evolving context database for AI agents

OpenViking is an open-source context database for AI agents. It unifies agent memory, knowledge resources, and skills into a single viking:// virtual file system, letting agents locate context with familiar file commands instead of querying an opaque vector store. Content is indexed into three tiers — L0 abstract, L1 overview, L2 details — at write time and loaded on demand, which cuts token usage and latency. Retrieval is directory-recursive: vector search first lands on the best-matching directory, then drills down layer by layer so results keep their surrounding context. Every query leaves an observable browsing trajectory that can be traced when answers go wrong. The project ships a CLI, server, benchmark harness, and integrations for Claude Code, Codex, Cursor, MCP clients, and more. It is well suited for engineers building agent memory, agentic RAG, or context engineering pipelines.

github.com · 19 min · Agent-Memory · Agentic RAG · Context Database
06-23

Loop Engineering

Loop Engineering proposes a shift from hand-prompting coding agents to designing autonomous loops: a system with five components (scheduled automations for discovery, worktrees for parallel isolation, skills to codify project context, plugins/connectors via MCP, and verifier sub-agents) that lets agents iterate without manual intervention. The post maps these primitives across Codex and Claude Code, noting that memory persisted outside the conversation (via AGENTS.md or Linear) is the critical sixth piece. The core insight is that loop design is harder than prompt engineering—the engineer's role moves from operator to system architect, while verification burden, comprehension debt, and cognitive surrender remain unresolved challenges that the loop itself cannot eliminate.

addyosmani.com · 14 min · Agent Architecture · Agent-Memory · Ai Tooling
06-17

Persistent Memory Engine for AI: Auto-Extract, Update, and Forget Intelligently

Supermemory is a memory and context layer for AI. It automatically extracts facts from conversations, builds and maintains user profiles, resolves contradictions, and intelligently forgets expired information. Combining hybrid search (RAG + memory), document processing, and live connectors (Google Drive, GitHub, etc.) into one API, it gives AI agents instant, personalized context. With plugins for Claude Code, Cursor, and more, it targets both developers integrating memory into apps and users wanting persistent AI memory across tools.

github.com · 14 min · Agent-Memory · Ai-Memory · Cloudflare
06-14

Hermes Agent: A Self-Improving, Multi-Platform AI Agent Runtime

Hermes Agent is a self-improving AI agent framework with a closed learning loop. It creates skills from experience, manages persistent memory across sessions, and operates over Telegram, Discord, Slack, and CLI via a single gateway. Any LLM backend can be used without code changes, and it runs on a $5 VPS or serverless infrastructure with near-zero idle cost. Built‑in cron scheduling, subagent delegation, and batch trajectory generation make it suitable for engineers and researchers who need an autonomous agent that evolves with use.

github.com · 11 min · Agent-Memory · Agents · CLI