Posts

1. What Codex Pet IsCodex Pets are optional animated companions built into the OpenAI Codex desktop app. They render as a floating overlay that stays on top of every other window, even when Codex itself is minimized, so the agent’s activity is visible while you work in other applications. A pet is a passive status surface with one active capability: if a pet shows a message while a task is running, clicking it opens a reply path back to the agent, turning the indicator into a small two-way channel.

OverviewThe 2025–2026 agentic‑AI shift moved from simple chat‑assistants to autonomous “workers” that operate on the cycle observe → plan → act → verify → recover. Modern platforms compete not on the underlying language model but on the agent harness — sandboxing, tool execution, memory, observability, deterministic orchestration, and governance. Successful systems minimise uncontrolled autonomy while preserving useful execution power. Methodology & MetricsPlatforms are grouped by their primary role (IDE, extensions, CLI agents, cloud agents, business platforms, browser agents, orchestrators, frameworks, open‑source agents, sensor agents, infrastructure and foundation models). Ranking within a group considers GitHub stars, installations/downloads, enterprise adoption, mentions in Q1–Q2 2026 industry reports, benchmark results, ecosystem activity, practical applicability and financial metrics. All metrics come from the original notes and require independent verification before use in reports.

Obsidian CLI - Obsidian Help

A concise summary of promptingguide.ai Covers core concepts, techniques, applications, risks, and best practices. Table of Contents Introduction LLM Settings Elements of a Prompt General Tips for Designing Prompts Basic Task Examples Core Prompting Techniques Advanced Prompting Techniques Agentic & Tool-Augmented Techniques Risks & Misuses Model-Specific Notes (ChatGPT) Tools & Libraries 1. IntroductionPrompt engineering is the discipline of developing and optimizing prompts to efficiently use large language models (LLMs) for a wide variety of applications.

Status: Normative Version: 2.0.0 Sources synthesized: Agent Skills spec (agentskills.io), anthropics/skills, anthropics/claude-code plugin-dev, openai/skills, github/awesome-copilot, Mintlify, Skills Directory, Geeksfino/openskills, addyosmani/agent-skills Scope: Cross-host portable core (Claude Code, Codex CLI, GitHub Copilot CLI, OpenClaw, compatible hosts) 1. Executive SummaryThis document defines a single, maximally strict specification for SKILL.md bundles, synthesized from all major skill ecosystem implementations and deep-research outputs across multiple AI providers. The portable profile is intentionally narrower than the full ecosystem because the source corpus agrees on the core artifact model — directory-scoped skill, required SKILL.md, YAML frontmatter plus Markdown body, progressive disclosure, and optional bundled resources — but diverges on frontmatter breadth, host-specific runtime controls, install/discovery paths, and metadata overlays.

Suggested filename: STAGE.md GoalOne markdown file = one self-sufficient pipeline stage. Each stage must: describe what it is declare its input dependencies declare its output contract link to previous and next stages be human-readable be parseable by a minimal Python agent work for any pipeline topology, not only requirements → design → tasks → scaffold Core IdeaEach stage file is markdown with a YAML frontmatter header. The frontmatter carries routing, validation, and execution metadata. The body carries the actual stage content.

Comparison Matrix Strategy Branches Release Cadence Complexity CI/CD Fit Multi-version Team Size Best For Trunk-Based main only, short-lived branches (<1 day) Continuous Low ✓ ✗ Any High-velocity SaaS GitHub Flow main + feature/* Continuous Low ✓ ✗ Small–Mid SaaS, startups, OSS GitLab Flow main + feature/* + env branches Continuous with gates Medium ✓ ◐ Mid Teams needing staging gates Ship / Show / Ask main + feature/* Continuous Low ✓ ✗ Small–Mid Balancing speed with review Stacked Diffs main + dependent chain Continuous Medium ◐ ✗ Mid–Large Large changes, atomic reviews Feature Flag Flow main (trunk-based + flags) Deploy ≠ Release Medium ✓ ◐ Mid–Large Decoupling deploy from release Release Flow main + release/* Scheduled Medium ◐ ✓ Large Discrete releases, Microsoft-style Gitflow main, develop, feature/*, release/*, hotfix/* Scheduled High ◐ ✓ Mid–Large Formal QA, multiple versions Legend: ✓ strong fit, ◐ partial, ✗ weak fit

Consolidated, validated reference for adding durable cross-session memory to Kimi Code CLI. All claims about external repositories were re-verified against upstream sources (May 2026). Unverified or contradicted claims from source drafts are marked or removed. VerdictBest default (validated) → agentmemory (rohitg00) MCP stdio, 51 tools, local iii-engine + embeddings, REST + viewer Officially supports Claude Code, Cursor, Gemini CLI, OpenCode, Codex CLI, Hermes, OpenClaw, pi. Kimi CLI not on official list, but standard MCP stdio block should work. Best minimal local → ai-memory-mcp (alphaonedev) Rust binary, single SQLite + FTS5, 97.8% R@5 on LongMemEval, 26 MCP tools, WAL mode, 79% smaller TOON output, no API cost. Best Kimi-native → kimi-mneme (claimed by source drafts) — UNVERIFIED ⚠️ Could not be located on GitHub or PyPI in May 2026. Do not include in install plan until existence confirmed. Best minimal Python → rekal (janbjorge) Python 3.11+, single SQLite + FTS5 + sqlite-vec (384-dim), 16 MCP tools, simple stdio, primary target Codex CLI / OpenCode. Best MCP graph route → mem0-mcp-selfhosted (elvismdev) Qdrant + optional Neo4j + Ollama, ~11 tools, fully offline. Best multi-agent → HeurChain Confirmed Kimi CLI read/write via MCP SSE in source drafts; Redis + vault, ACT-R decay, BM25 only. Best temporal reasoning → Graphiti (Zep) Neo4j/FalkorDB, fact validity windows, NER pipeline. Operationally heavy; specialized use case. Avoid → MemNexus, Mem0 Cloud, Zep Cloud (data leaves machine) Letta, Honcho (replace the agent rather than extend it) Raw vector DBs without memory logic (RAG poisoning over time) SSE-only servers for new setups (SSE deprecated in MCP spec March 2025) kimi-memory-mcp (SARPixelPioneer) — AgentSeal 75/100, DeepSeek required Kimi CLI Native Memory Surface — What You Get Out of the Box Feature What it gives What it does not give Session persistence Continue a session; context survives compaction via PreCompact/PostCompact hooks Durable searchable memory across sessions or projects AGENTS.md Project rules and conventions auto-loaded on session start Automatic extraction of decisions, debugging insights, or evolving facts Hooks (Beta) 13 lifecycle events configured as [[hooks]] in ~/.kimi/config.toml (SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, Notification, PreCompact, Stop, etc.); regex matchers, timeouts, blocking via exit code 2 Storage or retrieval backend by itself Skills (.kimi/skills/) Prompt-injected skill instructions, scoped Project > User > Extra > Built-in Persistent cross-session memory MCP (~/.kimi/mcp.json) Any standard MCP server via stdio or Streamable HTTP; managed with kimi mcp subcommand Automatic memory unless the agent actively calls memory tools Plugins Local toolkits packaged via plugin.json; OAuth credentials can be injected via inject block Long-term memory unless the plugin implements it Agent Flow Workflow orchestration Not a memory layer Key constraints: