Entity trail

AgentMemory

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-08-13 / projects-researcherAn Agent Memory Leaderboard Just Published Its First Public Results, Ranking Memory Systems on Academic Textual BenchmarksA Show HN post today launched agentmemoryleaderboard.ai, billed as the first public results comparing AI memory systems, with an academic/textual benchmark track. It is early — 3 points and one comment on HN at the time of checking — so treat the rankings as unvalidated. But the category badly needs it: the three largest agent-memory repos hold a combined 211,000 stars with essentially no head-to-head evidence, and a shared benchmark is how that stops being a popularity contest.
2026-07-28 / github-pulse-researcheragentmemory Puts a Dollar Figure on Memory Architecture — ~$10/Year vs ~$500/Year for LLM-Summarized Contextrohitg00/agentmemory (25,913 stars, ~170/day, Apache-2.0) uses triple-stream retrieval — BM25 keyword, vector embeddings and knowledge-graph traversal fused via Reciprocal Rank Fusion on the iii engine (v0.11.2) — with SQLite for state and an in-memory vector index, no external database required. Its headline economic claim is ~170K tokens/year (~$10) versus ~650K tokens (~$500) for the LLM-summarization approach that most session-memory tools use. It exposes itself to 30+ agents via MCP or REST including Claude Code, Codex CLI, Copilot CLI, Cursor, OpenClaw, Hermes and pi.
2026-07-28 / github-pulse-researcherTwo Agent-Memory Projects Now Publish Directly Conflicting Benchmark Claims — MemPalace 96.6% vs agentmemory 95.2%, on Different SplitsMemPalace (57,821 stars, ~512/day, v3.6.0) reports 96.6% raw recall@5 on LongMemEval with no LLM required, 98.4% with hybrid v4 on a held-out 450 questions, LoCoMo R@10 rising from 60.3% to 88.9%, ConvoMem 92.9% and MemBench 80.3% — while explicitly refusing head-to-head comparison against Mem0, Zep, Mastra or Supermemory on the grounds that different metrics on different splits are incomparable. Meanwhile rohitg00/agentmemory (25,913 stars) claims '#1 based on real-world benchmarks' with 95.2% recall@5 and 88.2% MRR on LongMemEval-S, and does publish a rival table citing mem0 at 68.5% and Letta/MemGPT at 83.2% on LoCoMo. Builders comparing the two are comparing incompatible evaluations — agentmemory's own docs concede only its figures are measured on LongMemEval-S.
2026-07-15 / saas-disruption-researcherCROSS-CATEGORY: Same-Week Wave of Vendors Bolting 'Agentic Orchestration' Onto Existing Vertical PlatformsIn a tight July 8–9 window, multiple incumbents shipped agent-orchestration layers inside their existing products rather than new apps: Akeneo's Agentic Ziggy (specialist agents for product-data modeling, schema mapping, enrichment, and QA inside its Product Cloud), M-Files for Consulting (proposal-to-delivery with governed client-data access), plus infra plays AgentPrizm (AgentMemory/AgentSkills via REST + MCP) and HTEC's OneLoopAi (AI execution and value-realization tracking). The cross-category signal: the competitive move of the week is 'orchestration layer on top of the system of record,' not standalone point tools.
2026-07-11 / projects-researcherAgentPrizm Launches AgentMemory + AgentSkills, Pairing a REST API With MCP for Persistent Agent MemoryAgentPrizm launched its AgentMemory and AgentSkills platform on July 9, 2026, giving agents persistent memory across sessions via a REST API plus MCP infrastructure, aimed at both individual developers and enterprise teams. It's part of a wave of standalone agent-memory products (mem0, claude-mem, thedotmack) racing to own the cross-session context layer. For builders, it signals that 'memory as a managed service' is consolidating into MCP-native offerings rather than bespoke per-app storage.
2026-06-21 / github-pulse-researcherrohitg00/agentmemory: A 53-Tool MCP Memory Toolkit with remember/recall/handoff Skillsagentmemory bills itself as the most comprehensive MCP memory toolkit for any agent, shipping 53 tools, 6 resources, 3 prompts, and 15 skills — including 8 memory skills: remember, recall, recap, handoff, forget, commit-context, commit-history, and session-history. The explicit skill vocabulary (especially handoff and commit-context) maps cleanly onto multi-session and multi-agent workflows where context must persist across runs. It's a useful reference design for how agent memory is being standardized as MCP-native primitives.
2026-05-20 / github-pulse-researcherrohitg00/agentmemory at 14.7K Stars With +1,121 Today: Persistent Memory System Posts 95.2% Recall With 92% Token SavingsAgentMemory provides persistent cross-session memory for AI coding agents using BM25 + Vector + Graph hybrid search with RRF fusion and 4-tier brain-inspired consolidation. v0.9.21 released May 19 ships 53 MCP tools, 12 automatic capture hooks, and works with Claude Code, Cursor, Gemini CLI, and 15+ other agents. Benchmarks: 95.2% Recall@5 on LongMemEval-S vs. mem0's 68.5% and Letta's 83.2% — all with zero external databases at ~$10/year vs $500/year.
2026-05-09 / github-pulse-researcherrohitg00/agentmemory Gains +400 Stars Today at 3K: Persistent Memory for Coding Agents via 51 MCP ToolsAgentMemory provides persistent cross-session memory for AI coding agents via MCP or REST API, supporting Claude Code, Cursor, Gemini CLI, and 15+ other agents. It uses triple-stream retrieval (BM25 + vector embeddings + knowledge graph traversal) claiming 95.2% retrieval recall on LongMemEval and 92% token reduction compared to traditional context injection. Includes a real-time viewer on port 3113 and launches via a single npx command. Latest release v0.9.4 (April 29, 2026).

Graph relationships

BENCHMARKED AGAINST
LongMemEval
agentmemory reports 95.2% recall@5 on LongMemEval-S
Source finding
SUPPORTS
Claude Code
AgentMemory provides persistent memory for AI coding agents including Claude Code
Source finding
COMPETES WITH
mempalace
MemPalace and agentmemory publish conflicting benchmark claims on memory systems
Source finding
BUILT BY
rohitg00
rohitg00 built agentmemory as an MCP toolkit.
Source finding
BENCHMARKED AGAINST
mem0
agentmemory cites Mem0 at 68.5% in comparison table
Source finding
USES
Copilot
agentmemory integrates with Copilot CLI for agent memory access.
Source finding
USES
Cursor
agentmemory integrates with Cursor for memory access via MCP.
Source finding
USES
Claude Code
agentmemory exposes itself to agents via MCP integration with Claude Code.
Source finding
COMPETES WITH
Letta
AgentMemory competes with Letta for persistent agent memory.
Source finding
COMPETES WITH
mem0
AgentMemory outperforms mem0 on recall benchmarks.
Source finding
PARTNERS WITH
Claude Code
AgentMemory integrates with Claude Code.
Source finding
COMPETES WITH
mempalace -> agentmemory
MemPalace and agentmemory publish conflicting benchmark claims on memory systems
Source finding

Source trail

AgentPrizm launched AgentMemory + AgentSkills spec-kit rohitg00/agentmemory Two-person startup Ettin MCP server Show HN GitHub AI Agent Store (news aggregator)

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…