vishesh9131 avatar

elephant

v0.4.5

by vishesh9131 · author: Vishesh Yadav

Carry coding sessions between AI harnesses.

What elephant does, in the publisher's words

Elephant

The model forgets. The elephant doesn't.

Claude hits quota. Codex keeps going. Automatic, local-first session continuity across AI coding harnesses.

  • the current objective and last completed state;
  • the last prompt and model response;
  • modified files and live Git state;
  • recent tool/model failures;
  • the latest 20 session events;
  • a redacted transcript reference when the host exposes one.

From the project README, punctuation lightly normalized · Open the README on GitHub

Skills
2
MCP servers
1
Stars
0
License
MIT
Repo created
2026-08-12
Last pushed
2026-08-18
Publisher type
User
Version
0.4.5

Links

Skills · 2

elephant
Save, label, pull, inspect, recover, protect, clean, and compact Elephant coding-session memory across Claude Code, Codex, Hermes, Pi, OpenCode, and other harnesses. Use when the user invokes or mentions Elephant commands such as memorize, exact, pull, resume, help, status, history, peek, note, doc…
resume
Recover and continue coding-agent work captured by Elephant across Claude Code, Codex, Hermes, or another harness. Use when the user asks where a previous session stopped, wants to resume work from another agent, or mentions a lost, quota-ended, or compacted coding session.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

MCP servers · 1

memorystdio
python3 ${PLUGIN_ROOT}/mcp/server.py

Read from the plugin's own mcp.json. We list environment variable names, never values.

Category

Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

context-handoff · agent-memory · coding-agents · session-continuity · productivity

Related by publisher and keywords

  • mem0mem0ai

    Cross-session memory and token savings for coding agents.

  • hindsightvectorize-io

    Long-term memory for AI agents. Recalls relevant past context before you answer and retains durable facts as you work, backed by Hindsight's retain/recall/reflect memory engine.

  • anarlogfastrepl

    Search local Anarlog meetings or connect to Cloud with OAuth.

  • bernsteinsipyourdrink-ltd

    The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no model in the coordination loop, so replaying a plan reproduces its task graph byte-identically.

  • Self-evolving second brain with 35 AI agent skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with a north-star acceptance gate, plus craft skills for writing, visual work, and a paired anti-slop design system for marketing and product UI. Works with Claude Code, Antigravity, Cursor, Kiro, Gemini CLI, Codex, and any Agent Plugins conformant client.

  • compartmentMaxFreedomPollard

    High-security, fully offline, encrypted vector memory for AI agents. AEAD-encrypted vault, locked by default after restart, no API key and no network at runtime.

Add the verified badge to your README[![Verified by AgentPluginsDirectory.com against Schema 1.0.0](https://agentpluginsdirectory.com/badge.svg)](https://agentpluginsdirectory.com/plugins/elephant)

✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.