AIAny
AI Client2026
Icon for item

AgentRecall

Centralizes indexing and management of local AI coding-agent sessions so you can search, view full context, migrate, resume, and restore conversations across agents and devices. Supports extensible local sources, AI summaries, optional Supabase sync, and Skills management.

Introduction

Most AI coding workflows scatter conversation history across agent-specific files and folders, which makes reuse, auditing, and cross-device recovery painful. This tool treats those fragmented session files as searchable, portable artifacts and gives you a single local UI to find, inspect, and continue work done by different coding agents.

What Sets It Apart
  • Unified local indexing: reads many agent formats (Claude Code / Codex by default; optional sources include CodeBuddy, CodeWiz, Cursor Agent, Trae, OpenCode, OpenClaw, Hermes, Qoder, and various CLI hooks) so you can search across otherwise incompatible session stores.
  • Resume & migrate workflows: can write portable session copies to target agent directories and return a resume command so you can continue a session in another agent or on another device without manually reconstructing context.
  • Configurable compression and AI-assisted retrieval: long sessions are automatically summarized using a configurable summary provider (custom API, built-in codex/claude fallbacks, or local truncation), and AI summaries/search help locate relevant exchanges inside long histories.
  • Optional cross-device sync under user control: uses the user's Supabase project and anon key for manual or hook-driven upload/restore; sync is opt-in and designed for single-user projects without sharing-sensitive defaults.
Who It's For and Trade-offs

Great fit if you routinely use multiple local or remote coding agents and need to recover or migrate past conversations, keep shared Skill assets in sync across machines, or analyze historical tool usage. Works well for developers who keep local session files and want a non-cloud-first, privacy-preserving index. Look elsewhere if you require a multi-tenant managed cloud service out of the box, need enterprise-grade RLS defaults for shared databases (the Supabase setup defaults to single-user patterns and requires manual hardening), or expect fully automated terminal launches when migrating sessions (the tool returns resume commands you run yourself).

Where It Fits

Acts as a desktop/local client for session management and lightweight MDM for agent assets: it complements agent runtimes (Claude Code, Codex, etc.) rather than replacing them, and is most useful when paired with an explicit sync workflow (Supabase hooks) or when you need searchable local archives of agent activity.

Information

  • Websitegithub.com
  • Authorszszz3, Blue-Berrys, G-Pegasus, mesakurax, LANSGANBS, forbbiden1, MeloMei
  • Published date2026/06/01

More Items

Hugging Face
AI Model2026

Preview agentic language model for research and engineering workflows that turns research questions into executable, verifiable workflows via tool use and long-context reasoning; built on a 744B-parameter MoE (GLM-5.2) with MIT-licensed BF16 and FP8 checkpoints.

Hugging Face
AI Model2026

Post‑trained 9B causal language model optimized for agentic workflows, tool use, coding, and long‑context instruction following. Uses a routing‑guided agentic post‑training pipeline that converts harness executions into training signal, improving agentic and coding benchmarks. Text‑only weights (safetensors/BF16), Apache‑2.0.

Hugging Face
AI Model2026

Multimodal foundation model for visual understanding, spatial reasoning and multi-step agent tool use — accepts text, multiple images and video at any resolution and supports long contexts (up to 128K tokens). Emphasizes fine-grained 2D/3D relations, affordance reasoning and embodied-AI planning.