AgentSidekick

Session Persistence

Saving and resuming agent sessions and chat history. As of 2026-11-21, 19 indexed products offer it (13 with full profiles), in 4 forms: 10 MCP servers, 4 Agent skills, 3 Frameworks, 2 IDE extensions. 2 were published in the last 90 days, against 2 in the 90 days before. LangGraph has the most GitHub stars, 96% of the total across 14 products with their own repository.

CapabilitySegment label: Thin DERScored as an opportunity

Available as

All in the directory

Profiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.

MCP servers 10 indexed · 4 profiled

Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms

Session Persistence: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1claude-historian-mcp📜 An MCP server for conversation history search and retrieval in Claude CodeVvkmnn18019d ago
2claudexPersistent memory + FTS5 search MCP server for Claude Code conversation history.kunwar-shah985mo ago
3claude-code-conversation-search-mcpSearch Claude Code conversation history with natural language queries across all projectsTonySimonovsky51y ago
4Rootz ArchiveSearch your local Claude Code archive. For continuous capture, use the Rootz Archive plugin.rootz.global41mo ago

Agent skills 4 indexed · 4 profiled

Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms

Session Persistence: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1distributed-llm-pretraining-torchtitanProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.Orchestra-Research—1mo ago
2pytorch-fsdp2Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.Orchestra-Research—1mo ago
3agent-memory-systemsDesign tenant-scoped memory, retrieval and retention for agents. Use when planning RAG, conversation history, vector stores or remembering across sessions.sickn33—1d ago
4memory-searchSearch conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when", "find previous conversation", "check history", or before starting work to recall prior decisions.davila7—today

Frameworks 3 indexed · 3 profiled

No compatibility evidence is collected for this form.

Session Persistence: Frameworks by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1LangGraphLow-level orchestration framework that models agents as stateful graphs with checkpointing, human-in-the-loop interrupts and durable execution.LangChain45ktoday
2chidoriThe agent framework where every run is durable, replayable, and resumable by default.ThousandBirdsInc1.4k5d ago
3prodagentA minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核,理解 LangGraph/ADK 底层的工作原理limenagent1501mo ago

IDE extensions 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Session Persistence: IDE extensions by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1Claude Code and Codex Assist - Chat History, Diff & Usage AnalyticsChat history for Claude Code, Codex, OpenCode, Grok & Copilot — browse, search, diff & resume sessions; track usage, cost & quota. MCP server gives your AI agents memory of past chats across CLIs. Free, with optional Pro.A. G. Software Technologies42today
2Secondary TerminalSidebar terminal for VS Code with AI agent awareness (Claude Code, Copilot, Gemini, Codex, Antigravity), split views, session persistence, and full IME support.s-hiraoku22today

Which platforms these forms can reach

All platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Claude Code6
Codex2
OpenCode1
Google Antigravity1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

No integrations named

None of the products matched here names a tracked third-party service.

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
session persistence1
checkpointing6
resume sessions1
conversation history9
chat history storage0
state persistence2

Segment statistics

Whole catalogue (19 indexed products). Calculated 2026-11-21.

19DERIndexed products13 with full profiles
2DERLaunched, last 90 days2 in the 90 days before
UnknownDERMomentum vs catalogueFewer than 5 dated launches in 180 days
96%DERLargest project's share of starsAcross 14 products with their own repository
0.922DERConcentration (HHI)About 1 equal-sized projects’ worth; highly concentrated
15SRCMedian starsPer product with its own repository
89%DEROpen sourceMarked open source; unknown counts as not

Thin. Among the smallest 30% of capabilities, and launches are not outpacing the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.922 means stars are spread as if across about 1 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.

Scored as an opportunity

Score breakdown

Coverage gap: Session Persistence: score 60.0 HEU, competition High, confidence Low. Only 19 indexed products match "Session Persistence", against 850 in Memory & State overall.

Limits

  • Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
  • Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
  • Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
  • Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.

Page data last updated .