Every past session, subagent, and workflow -- queryable by your agent, browsable by you
Stop babysitting local AI agents. Just notifications, approve, and resume your Codex,Pi,Grok, or Claude code sessions anywhere. 0-Intrusion mobile control bridge via Telegram/微信/飞书. No hooks, no skills, no MCP.
Collaboration in the age of agentic engineering
USL is the storage-first reference implementation of the Agent Session Protocol (ASP). ACP handles the live present (editor↔agent interaction); ASP handles the durable past and cross-runtime migration; USL is the storage engine behind ASP.
Portable session history for AI agents and harnesses.
💻 iTerm2 keyboard shortcut to fork the active coding agent CLI session into a new tab. Suports cross-agent session forking, e.g. codex <-> claude, claude <-> opencode, codex <-> opencode
跨编码 Agent 无缝迁移会话上下文，让Claude Code、Codex之间的会话上下文自由迁移、复制和同步。
Spider Web is a provider-neutral interoperability layer for AI coding-agent sessions. It captures the structured working state of an agent run into a standard session model and packages it into portable .spider-egg archives.
Strict TypeScript port of the coding-agent session finder CLI.
ASIF - an open, vendor-neutral specification for exchanging AI agent sessions, including conversation history, attachments, tool interactions, and continuation state.
One view of all your Claude Code, Codex, OpenCode, Pi, OpenClaw, and Hermes agents' history. Pin your active threads, search every session, jump back in with one keystroke — in tmux or terminal (CLI).
Make every coding agent faster, cheaper, and more accurate with a persistent local code graph that learns from each session.
Agent Notebook — a local-first knowledge notebook co-written by you and your agents.
StationTrail exports local station and agent-session logs to portable miseledger.adapter.v1 JSONL. Local-only, no network calls.
Cross-session full-text recall for DeepSeek Harness: the model-facing recall tool searches past session transcripts via ctx.sessionQuery, with a persistent FTS index
A vibe coding assistant that runs in your terminal
Retrospective evaluation for DeepSeek Harness agent sessions: deterministic grade cards + cross-session regression diffs over persisted logs — no benchmarks, no LLM judges
Personal fork of spool-lab/spool (renamed upstream to paperboytm/spool). Local patches: Codex subagent folding, Pi as a desktop source, agent-grouped sidebar. Upstream is the source of truth; see FORK.md.
NPKILL-style cleanup for Claude, Pi, OMP, and GitHub Copilot Chat agent session remnants
Node CLI for compressing cold AI coding-agent sessions with verified byte-exact restore.
To associate your repository with the agent-sessions topic, visit your repo's landing page and select "manage topics."