Coding-agent memory

11 systems in the coding-agent memory category of the AI Agent Infrastructure Landscape, grouped by maturity tier.

Tier 1 — battle-tested (5)

  • Augment Code Real-time semantic Context Engine + curated Agent Memory

    Real-time knowledge graph indexed from connected repos + commit history + CI/CD + tickets + docs. Separate Agent Memory layer (Sept 2025) captures session decisions/corrections/goals as discrete items with developer review/approval UI. M…

  • Devin (Cognition) Server-side Knowledge + auto-Repo Knowledge

    Structured Knowledge items stored server-side. Three-tier scope: repo-pinned (always injected), global (recall by relevance), org/enterprise (visible to org members). Auto-generates Repo Knowledge from repo structure each session; reads …

  • Mistral Vibe (Remote Agents) + Mistral Medium 3.5 Cloud-hosted async coding agents with teleportable session state

    Vibe is Mistral's cloud-hosted coding-agent platform: each session runs in an isolated sandbox with task state, history, and approvals. Spawnable from CLI or Le Chat, with parallel execution. Local CLI sessions can be "teleported" to the…

  • OpenAI Codex (cloud agent) File-backed ~/.codex/memories + Chronicle

    Memory under ~/.codex/memories/ : summaries, durable entries, recent-input logs, supporting evidence — generated in background after sessions go idle. Chronicle (opt-in macOS preview) uses screen-capture to seed memory. Off by default; o…

  • Replit Agent Project-files-as-memory + Temporal orchestration

    No documented built-in persistent semantic memory store. Session duration expanded to 200 min (Agent 3); Agent 4 shifts toward persistent runtimes. Temporal used for orchestration durability, not semantic memory. Cross-session memory rel…

Tier 2 — production-ready (6)

  • Aider Per-repo chat history file + YAML config

    Appends conversation turns to .aider.chat.history.md in project root. restore_chat_history defaults to false — no automatic replay into new sessions. Community /session save command for JSON state snapshots. .aider.conf.yml carries stati…

  • Bolt.new (StackBlitz) WebContainer file system

    In-browser WebContainer (Rust-backed shared memory) is the implicit state store. No dedicated memory abstraction — project files are the state. Team plan adds shared workspaces + GitHub integration.

  • Continue.dev Memory MCP KG-backed memory via MCP

    Official Memory MCP (Mar 2025) backed by a knowledge graph. Memory is injected via MCP rather than native to the Continue core. Scope depends on MCP server deployment (local or shared).

  • Lovable /docs folder + Knowledge Panel

    Long-term context stored as files in /docs that the agent reads on each session. Agent Mode (default since July 2025) holds working context within session but doesn't persist cross-session beyond filesystem state.

  • Sweep AI GitHub-thread-as-implicit-memory

    No dedicated persistent memory layer. Operates as a GitHub App — reads issue + codebase fresh on each trigger. Some context implicit in the PR/issue threads it created previously.

  • Tabnine Org-level Context Engine + Tabnine Agents

    Enterprise Context Engine builds a multi-dimensional knowledge graph from repos + CI/CD + PRs + tickets + docs at the org level. Individual completions stay session-scoped. Tabnine Agents (Nov 2025) adds team-shared agent context.