Context Engineering

Junior’s first memory system cut one analytics task from about 3 minutes to 1 minute in early tests, with tokens down two-thirds and tool calls down 60%. The feature moves persistent task learning into the agent loop, though the results are still internal.

Builders released reusable loop artifacts this week, including a Loop Library Skill, repo templates, and published control-loop definitions for docs sweeps, onboarding checks, and error triage. It matters because teams are turning one-shot prompting into persistent agent runs with explicit stop conditions and shared repo state.

Plannotator 0.21.0 added direct document editing, an embedded CLI agent for co-context, first-class HTML handling, and Bedrock and Vertex support. It matters because the tool is moving from annotation-only review toward persistent IDE-like agent sessions with shared file diffs and cloud model backends.

Perplexity rolled out Brain, a self-updating context graph that carries prior sessions, files, and decisions into new Computer tasks. In research preview for Max users, it matters because Perplexity says the memory layer improves correctness and recall while lowering per-task cost on history-dependent work.

Two days after Factory 2.0 launched, Factory added AutoWiki, which turns a repo into structured engineering docs that update on every push and can be generated from Droid with /wiki. The feature keeps architecture and request-path context aligned with the live codebase.

Z.ai released GLM-5.2 MIT-licensed open weights with 1M context and broad runtime support. Vendor and arena results put it near frontier closed models on long-horizon coding.

Codex users are having the agent write its own `/goal` and sub-agent goals, with OpenAI-side commentary describing that as a built-in meta-prompting pattern. The workflow turns long autonomous runs into a tighter control loop, but users still review goals first so a bad objective does not burn tokens for hours.

Users are using Fable 5 as a planner and long-run orchestrator while pushing implementation and heavy reasoning to Opus and Codex. The setup keeps Fable on supervision and planning, so teams can track execution through live status pages on larger tasks.

Hyperbrowser shipped a Claude Code harness, InsForge showed a Fable run drop from 5.5M to 2.3M tokens, and Higgsfield published new MCP workflows. These tools add reusable harness, context, and interface layers around Fable for more controlled runs.

Matt Pocock's /teach skill installs with npx skills add mattpocock/skills --skill teach and runs structured strategy lessons inside a Claude agent. Follow-up posts add primary-source reading to the lessons and point to a larger dedicated repo.

Anthropic published Fable-specific guidance for Claude Code and API, emphasizing the /model switch, higher default effort, simpler prompts, and /goal-style verification loops. The Claude Code team says older prompt scaffolds can work against Fable's longer sessions.

Practitioners shared repeatable setups for multi-hour Claude runs using auto approvals, dynamic workflows, cloud sessions, and critique loops. One large-codebase sweep reported 144 bugs fixed in about four hours with fewer false positives under model critique.

Codex usage moved further into phone-first workflows, with iOS dictation loops, background voice capture, and app updates like searchable settings and restored state. The comparisons still flag rough spots in multi-thread UX, Windows support, and cases where CLI tabs or cloud agents are easier to manage.

A community workflow broke long-running Codex goals into six required fields, then added an eight-item preflight checklist and helper tools. The structure is meant to reduce runs that drift, stop early, or claim completion without an objective verification step.

OpenAI rolled out a more capable ChatGPT memory system that keeps context across conversations, shows a reviewable memory summary, and doubles memory for US Plus and Pro users. The change matters because persistent context becomes a first-class product feature with explicit controls instead of a static saved-memories note list.

Weaviate introduced Engram, a dedicated agent memory service with async writes, semantic topic grouping, tenant scopes, and composable pipelines. It matters because teams can add a hosted memory layer for agent stacks without stitching custom memory workflows into each application.

GitHub Copilot now supports a 1M-token context window and configurable reasoning levels in VS Code, Copilot CLI, and the Copilot app. It matters because larger repo context and explicit effort controls arrive in the same surfaces teams already use for agent-assisted development.

Builders added /dynamic orchestration, custom-model routing, and repo runbooks around Codex as users exposed new session lifecycle controls in the app. That makes Codex a better fit for long-running, multi-context coding work.

Opus 4.8 can accept new system-role instructions after a user turn while keeping earlier prompt segments cacheable. That lets long-running agents update constraints mid-loop without replaying the full system prompt on every call.

Independent developers released browser-control MCP tooling, repo-context graphing and packaging utilities, and token-compression helpers for coding agents. The cluster matters because agent workflows are now adding browser control, context packing, and cost controls as external infrastructure instead of waiting on raw model upgrades alone.

A new MeMo paper and several community memory systems converged on keeping knowledge outside the base model through recipe files, semantic and autobiographical stores, and background reconsolidation. The pattern matters because engineers are treating context loss as a systems problem instead of only asking for larger context windows.

Practitioners published reusable Codex workflows for project audits, memory-driven skill packaging, mobile delegation, and remote computer use. Try the prompt-and-steps patterns if you want to adapt Codex across repos and devices.

Independent builders published reusable skills infrastructure across coding agents, including Project Think preview support, handoff docs, and an htmx v4 skill pack. That matters because skills are starting to work like portable workflow units instead of one-off prompt snippets inside a single tool.

Independent Codex users published Obsidian memory setups, reusable skill prompts, auto-triage flows, and Cloudflare-backed runners for longer jobs. That matters because Codex is being wrapped into persistent workspaces and operator-defined subagents instead of one-shot chats.

Developers say Codex v0.133.0 improved compaction, remote-control workflows, and Chrome-driven Colab runs after `/goal` became default. The same update window also brought easier skill discovery and new diff options, though some users saw approval-pause regressions in full-access mode.

Claude Console now shows which message, system prompt, tool, or model change caused a cache miss and how many tokens it cost. That matters because teams can trace prompt-cost regressions to specific edits instead of debugging cache churn blind.

Notion opened a developer platform with an External Agents API plus Workers, webhooks, and a headless CLI. The release lets external agents query Notion, extend workflows, and stay in sync with other systems.

Independent builders shipped new specs and tools for richer agent output, including Markdown Experience Guidelines and Plannotator’s HTML render-and-annotate flow, while practitioners shared repeatable HTML explainer workflows. The cluster matters because teams are moving beyond raw Markdown toward output surfaces that can carry charts, interaction, review context, and persistent knowledge-base structure.

A day after HTML artifacts surfaced as a Claude Code workflow, Anthropic promoted a `frontend-slides` plugin with direct install commands and artifact publishing. The rollout sharpened a real workflow split: teams are using HTML for human review and demos, while keeping markdown or MDX for token-efficient agent context.

A cluster of Claude Code users, guides, and companion tools shifted from Markdown toward HTML artifacts for code review, dashboards, and explainer pages. The pattern matters because richer outputs are easier to inspect and share during long agent workflows, though several builders note the token cost is materially higher than Markdown.

Anthropic added Dreaming in research preview plus public-beta Outcomes, multiagent orchestration, and webhooks to Claude Managed Agents. Teams should try the new grader loops and shared-container sub-agents if they want more control over long-running agent work.

Builders shared concrete Symphony, create_agent, and MCP setup guides after arguing that model switching is easy but harness switching is not. The playbooks matter because they make harness engineering more repeatable, so teams can copy tested tooling and integration patterns.

GitHub expanded semantic indexing beyond GitHub and Azure DevOps remotes, so Copilot can search across more workspace types and repositories inside @code. That improves agent context retrieval in local workflows, while the same release also adds chat-history recall and prompt-eval tooling.

mattpocock/skills hit the top of GitHub Trending as reusable `SKILL.md` packs for grilling specs, writing PRDs, and enforcing TDD spread across coding-agent workflows. The format is starting to look like a distribution layer for agent behavior, with faster install tooling and third-party skills shipping around the same pattern.

OpenAI added Chronicle, a Codex preview that turns recent screen context into reusable memories for errors, files, docs, and workflows. The macOS Pro-only feature stores local memory unencrypted and can burn rate limits quickly, so watch prompt-injection risk before relying on it.

Builders say they are already passing Claude Design prototypes into Claude Code, wiring live backends through AGENTS.md, and recreating the flow in custom orchestrators. Try this if you want a faster handoff from mockup to full-stack build, but expect early workflow rough edges.

OpenClaw 2026.4.15 adds Anthropic Opus 4.7, bundled Gemini TTS, bounded memory reads, and transport self-heal fixes. The release targets context and reliability issues users had been reporting this week.

Codex 0.120 introduced per-project memory extension files and Realtime V2 progress streaming for background agents. Separate app findings also showed an unreleased Scratchpad view that can start parallel Codex chats from a task list, which may change how teams queue work.

Nous Research added MiniMax M2.7, Xiaomi’s MiMo V2 Pro, a SuperMemory plugin, and expanded Manim support to Hermes through partner integrations. The additions give users new hosted model options, a shared memory backend, and more complete technical-animation tooling to try in workflows.

OpenClaw 2026.4.7 adds a headless inference hub, memory-wiki, session branch and restore, and webhook-driven TaskFlows. Composio also shipped a CLI for secure app authentication, so users can expand OpenClaw from a local coding harness into a broader agent runtime.

Bram Cohen used the Claude Code leak to argue that prompt-only development produces bad software, while a separate 250-hour syntaqlite build said the durable version arrived only after a Python-to-Rust rewrite. Practitioners say specs, tests, linters, repo skills, and codebase context are the controls that keep coding agents maintainable.

Hermes Agent added direct /claude-code orchestration and cron-time script hooks, and the team also shipped Hermes-focused datasets and agent-tuned model variants. The update turns Hermes into a harness that can steer Claude Code and inject recurring context automatically.

Clawback turns leaked Claude Code verification patterns into stop, pre-tool, post-tool, and post-compaction hooks. It replaces prompt-only guardrails with deterministic checks and shows how fast the source-map leak is becoming third-party control layers.

Nous released Hermes Agent v0.7.0 with an extensible memory plugin system, rotating credential pools, Camofox browser support, and inline diff previews. The update pushes the framework closer to production use, so teams can test the new failure handling and interface split before adopting it.

A Boris Cherny guide maps Claude Code mobile sessions, /teleport, /loop, hooks, worktrees, /batch, and custom agents into one workflow set. Use it to turn scattered commands into repeatable patterns for long-running coding sessions across terminal, desktop, and cloud.

Two new guides map how Claude Code teams are using `.claude/`, `CLAUDE.md`, commands, agents, skills, and global rules. The overlap matters because commenters favor short instructions and a small number of repeatable guardrails over larger prompt stacks.

ChatGPT now saves uploaded and generated files into an account-level Library that can be reused across conversations from the web sidebar or recent-files picker. It removes repetitive re-uploading and makes past PDFs, spreadsheets, and images part of a persistent working context.

Nous Research said Hermes Agent crossed 10,000 stars, while users reported easy migrations from OpenClaw and stable long-running use. If you test it, focus on persistent memory, MCP browser control, and delegation behavior under real workloads.

Agent Flywheel lays out a planning-first workflow built on beads, agent mail, swarms, and TUI inspection for very large coding runs. It is useful because the guide exposes coordination primitives and review loops, not just benchmark screenshots.

Anthropic rolled Projects into Cowork on the Claude desktop app, giving each project its own local folder, persistent instructions, and import paths from existing work. It makes Cowork more practical for ongoing tasks, though teams should test current folder-location limits.