aictx
Active·★ 59·MIT·Updated 2026-06-17
AICTX provides operational continuity for AI coding agents by preserving execution state, active work, and context across sessions. It helps agents resume work from factual evidence, preventing redundant discovery and improving efficiency.
#AI Agent#Context Management#Developer Tools#Operational Continuity#Session Management#Failure Memory#Workflow Automation
01
Features
01Work State Preservation: Preserves active task, hypothesis, and verification state across sessions.
02Failure Memory: Stores structured patterns of observed command/test/build failures.
03Inspectable Continuity View: Generates local Markdown/Mermaid reports of the repository's operational state.
04Task Context Packs: Compiles focused, read-only context for specific tasks.
05Repo-Local Storage: Stores all continuity data locally within the repository.
02
Compatibility
Python
Runtime
Verified via docs
Codex
AI Agent
Verified via docs
Claude
AI Agent
Verified via docs
GitHub Copilot
AI Agent
Verified via docs
CLI
Interface
Verified via docs
03
Quick start
1
$ pip install aictx
2
$ aictx install
3
$ aictx init
04
Use cases
↳Agent Session Resumption: Enables AI coding agents to resume work from the last useful state instead of starting cold.
↳Preventing Rework: Helps agents avoid repeating known failures or rediscovering repository structure.
↳Enhanced Agent Performance: Provides crucial context for agents like Codex, Claude, and GitHub Copilot.
↳Operational State Review: Allows users to inspect and review the agent's active work state and decisions locally.
↳On-Demand Task Context: Agents can request bounded, read-only context for focused tasks.
05
Alternatives
EGC★ 67
Your AI remembers your project across sessions and tools. Local-first MCP runtime with persistent memory, shared workflows, and plug-and-play integration.
infimium-agent★ 25
Infimium helps agents find the right code, docs, and dependencies — before they edit. Local-first, open-source, MCP-compatible.
AgentRecall-X★ 371
Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.
clarilayer★ 82
Stop re-explaining your data to your AI every session. The individual-analyst context layer, delivered over MCP (Claude Code / Cursor / Codex).
state-memory-mcp★ 48
Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to prevent session context bloat and speed up development.
mori★ 32
mori MCP server — A shared memory layer for AI coding agents — one that compounds.
Comments
Log in to leave a comment
No comments yet. Be the first!